---
title: "Interpretable Long-Form Legal Question Answering with"
description: "The authors build a retrieve-then-read system that writes detailed answers to questions about any… 88 references, cited by 72 papers here."
authors: ["Antoine Louis", "Gijs van Dijck", "Gerasimos Spanakis"]
year: 2023
venue: "arXiv:2309.17050"
source: "https://arxiv.org/abs/2309.17050"
doi: "10.48550/arxiv.2309.17050"
arxiv: "2309.17050"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/louis-2023-interpretable-long-form-legal-question/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/louis-2023-interpretable-long-form-legal-question/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/5/) / Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models

# Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models

**Authors:** Antoine Louis, Gijs van Dijck and [Gerasimos Spanakis](https://md.research.elamur.ai/free/en/authors/gerasimos-spanakis/) · **Year:** 2023 · **Venue:** [arXiv:2309.17050](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-conference-on-artificial-intelligence/) ([Proceedings of the AAAI Conference on Artificial Intelligence 2023](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-conference-on-artificial-intelligence/2023/)) · **Publisher:** [Association for the Advancement of Artificial Intelligence](https://md.research.elamur.ai/free/en/publishers/association-for-the-advancement-of-artificial-intelligence/) · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2309.17050) · [PDF](https://arxiv.org/pdf/2309.17050) · [DOI 10.48550/arxiv.2309.17050](https://doi.org/10.48550/arxiv.2309.17050) · [arXiv 2309.17050](https://arxiv.org/abs/2309.17050) · [OpenAlex](https://openalex.org/W4393161188)

**Citations:** 85 citations (OpenAlex, 2026-10-14) · [72](https://md.research.elamur.ai/free/en/papers/louis-2023-interpretable-long-form-legal-question/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses legal aid for laypeople. Existing legal QA systems either cover one narrow area of law or return only yes/no answers and short spans. The authors build a retrieve-then-read system that writes detailed answers to questions about any area of statutory law. A lightweight bi-encoder first fetches relevant legislative articles. An instruction-tuned LLM then composes an answer and points to the paragraphs that support it. The reader is adapted in two ways: in-context learning, and parameter-efficient finetuning on top of a frozen, quantized base model.

To train and test such systems, the authors release LLeQA. It is a French dataset of 1,868 expert-written questions and answers grounded in a corpus of 27,942 Belgian statutory articles. Automatic scores look reasonable, and finetuning helps every reader. A manual check, however, shows fluent answers that often contain invented facts. Retrieval also remains a bottleneck. The work matters as a rare expert-annotated, long-form legal QA benchmark. It also warns against trusting overlap metrics alone.

## Key points
- **What LLeQA extends:** it builds on BSARD (1,108 questions, 22,633 articles), adding 760 questions (+69%) and 5,308 articles (+23%).
- **New annotations:** a question taxonomy, the jurisdictions involved, paragraph-level references and full answers written by jurists.
- **Data source and filtering:** the questions come from the Belgian non-profit Droits Quotidiens. About 2,550 were collected. Items with missing or overly vague references, or with references outside the corpus, were removed, and duplicates were merged.
- **Synthetic labels:** part of the paragraph-level relevance labels were generated with gpt-3.5-turbo-0613, which picked the paragraphs that support each answer.
- **Retrieval results:** the dense retriever was finetuned on roughly 1.5k in-domain examples and beats strong baselines. Still, on average fewer than half of the relevant articles reach the top 5.
- **Generation results:** readers were scored with METEOR. WizardLM and Vicuna did best, and finetuning lifted scores to around 20 (WizardLM 20.4).
- **Rationale results:** rationale-extraction F1 stayed close to zero for most models.
- **TÜLU's weakness:** its answers were short, which the authors link to its instruction data averaging 98.7 words per completion.

## Interesting ideas
- **Citations as paragraph markers:** the reader outputs identifiers of the paragraphs it relied on, rather than free-text explanations. Its justifications can then be scored with plain F1 against gold markers. This could suit any grounded generation task that needs checkable citations.
- **LLM-made fine-grained labels:** the authors had an LLM pick the supporting paragraphs inside articles that experts had already marked as relevant. This is a cheap way to turn coarse document-level gold labels into finer ones. It is useful wherever expert annotation is costly.
- **Pairing metrics with manual reading:** even a small manual check of 10 samples exposed hallucinations that METEOR missed. Keeping a manual review step alongside automatic scores is a good habit for long-form generation.
- **Checking the training data's answer length:** a reader trained mostly on short completions tends to produce short answers. When picking a base model for long-form output, it pays to check the typical completion length of its instruction data.
- **Measuring the retriever separately:** reporting retrieval quality on its own shows when generation errors stem from missing evidence rather than from the reader. This helps decide where to spend effort in RAG pipelines.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Maastricht University](https://md.research.elamur.ai/free/en/universities/maastricht-university/) — University, Maastricht, Netherlands · 7 works · 605 citations

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🤝 Political Science and International Relations](https://md.research.elamur.ai/free/en/shelves/social-sciences/political-science-and-international-relations/) · 206 works · [⚖️ Law](https://md.research.elamur.ai/free/en/shelves/social-sciences/law/) · 84 works

🧭 Topics (3): [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 487 works · [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 552 works · [⚖️ Legal AI](https://md.research.elamur.ai/free/en/topics/legal-ai/) · 150 works

💡 Concepts (1): [💡 Retrieval-augmented generation](https://md.research.elamur.ai/free/en/concepts/retrieval-augmented-generation/) · 50 works

## Cite

Cite as: Antoine Louis, Gijs van Dijck and Gerasimos Spanakis. 2023. Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models. arXiv:2309.17050.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{louis2023interpretable,
  title = {{Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models}},
  author = {Antoine Louis, Gijs {van Dijck} and Gerasimos Spanakis},
  year = {2023},
  doi = {10.48550/arxiv.2309.17050},
  eprint = {2309.17050},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2309.17050}
}
```

- [← previous Are aligned neural networks adversarially aligned?](https://md.research.elamur.ai/free/en/papers/carlini-2023-aligned-neural-networks-adversarially-aligned/)
- [next → Lawyer LLaMA Technical Report](https://md.research.elamur.ai/free/en/papers/huang-2023-lawyer-llama-technical-report/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/5/)

## References

88 references, 44 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Balmer, N. J.; Buck, A.; Patel, A.; Denvir, C.; and Pleasence, P. 2010. Knowledge, capability and the experience of rights problems. London: PLEnet. [find](https://scholar.google.com/scholar?q=Balmer%2C+N%2E+J%2E%3B+Buck%2C+A%2E%3B+Patel%2C+A%2E%3B+Denvir%2C+C%2E%3B+and+Pleasence%2C+P%2E+2010%2E+Knowledge%2C+capability+and+the+experience+of+rights+problems%2E+London%3A+PLEnet%2E)
2. Banerjee, S.; and Lavie, A. 2005. [METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments](https://md.research.elamur.ai/free/en/papers/banerjee-2005-meteor-automatic-metric-mt-evaluation/). In Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and Summarization co-located with the 43rd Annual Meeting of the Association for Computational Linguistics, 65–72. Association for Computational Linguistics.
3. Bastings, J.; Aziz, W.; and Titov, I. 2019. [Interpretable Neural Predictions with Differentiable Binary Variables](https://md.research.elamur.ai/free/en/papers/bastings-2019-interpretable-neural-predictions-differentiable-binary/). In Proceedings of the 57th Conference of the Association for Computational Linguistics, 2963–2977. Association for Computational Linguistics.
4. Baumel, T.; Eyal, M.; and Elhadad, M. 2018. Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models. CoRR, abs/1801.07704. [↗](https://arxiv.org/abs/1801.07704)
5. Berant, J.; Chou, A.; Frostig, R.; and Liang, P. 2013. [Semantic Parsing on Freebase from Question-Answer Pairs](https://md.research.elamur.ai/free/en/papers/berant-2013-semantic-parsing-freebase-question-answer/). In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, 1533–1544. ACL.
6. Bhattacharya, P.; Hiware, K.; Rajgaria, S.; Pochhi, N.; Ghosh, K.; and Ghosh, S. 2019. A Comparative Study of Summarization Algorithms Applied to Legal Case Judgments. In Advances in Information Retrieval - 41st European Conference on IR Research, volume 11437 of Lecture Notes in Computer Science, 413–428. Springer. [find](https://scholar.google.com/scholar?q=Bhattacharya%2C+P%2E%3B+Hiware%2C+K%2E%3B+Rajgaria%2C+S%2E%3B+Pochhi%2C+N%2E%3B+Ghosh%2C+K%2E%3B+and+Ghosh%2C+S%2E+2019%2E+A+Comparative+Study+of+Summarization+Algorithms+Applied+to+Legal+Case+Judgments%2E+In+Advances+in+Information+Retri)
7. Biewald, L. 2020. Experiment Tracking with Weights and Biases. Software available from wandb.com. [find](https://scholar.google.com/scholar?q=Biewald%2C+L%2E+2020%2E+Experiment+Tracking+with+Weights+and+Biases%2E+Software+available+from+wandb%2Ecom%2E)
8. Bromley, J.; Guyon, I.; LeCun, Y.; Säckinger, E.; and Shah, R. 1993. Signature Verification Using a Siamese Time Delay Neural Network. In Advances in Neural Information Processing Systems, volume 6, 737–744. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Bromley%2C+J%2E%3B+Guyon%2C+I%2E%3B+LeCun%2C+Y%2E%3B+Sa%CC%88ckinger%2C+E%2E%3B+and+Shah%2C+R%2E+1993%2E+Signature+Verification+Using+a+Siamese+Time+Delay+Neural+Network%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+6%2C+)
9. Brown, T. B.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; Agarwal, S.; Herbert-Voss, A.; Krueger, G.; Henighan, T.; Child, R.; Ramesh, A.; Ziegler, D. M.; Wu, J.; Winter, C.; Hesse, C.; Chen, M.; Sigler, E.; Litwin, M.; Gray, S.; Chess, B.; Clark, J.; Berner, C.; McCandlish, S.; Radford, A.; Sutskever, I.; and Amodei, D. 2020. [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). In Advances in Neural Information Processing Systems, volume 33. Curran Associates, Inc.
10. Camburu, O.; Shillingford, B.; Minervini, P.; Lukasiewicz, T.; and Blunsom, P. 2020. Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 4157–4165. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Camburu%2C+O%2E%3B+Shillingford%2C+B%2E%3B+Minervini%2C+P%2E%3B+Lukasiewicz%2C+T%2E%3B+and+Blunsom%2C+P%2E+2020%2E+Make+Up+Your+Mind%21+Adversarial+Generation+of+Inconsistent+Natural+Language+Explanations%2E+In+Proceedings+of+the+58th)
11. Chalkidis, I.; Androutsopoulos, I.; and Aletras, N. 2019. [Neural Legal Judgment Prediction in English](https://md.research.elamur.ai/free/en/papers/chalkidis-2019-neural-legal-judgment-prediction-english/). In Proceedings of the 57th Conference of the Association for Computational Linguistics, 4317–4323. Association for Computational Linguistics.
12. Chalkidis, I.; Fergadiotis, M.; Tsarapatsanis, D.; Aletras, N.; Androutsopoulos, I.; and Malakasiotis, P. 2021. [Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-paragraph-level-rationale-extraction-through/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 226–241. Association for Computational Linguistics.
13. Chen, A.; Yao, F.; Zhao, X.; Zhang, Y.; Sun, C.; Liu, Y.; and Shen, W. 2023a. EQUALS: A Real-world Dataset for Legal Question Answering via Reading Chinese Laws. In Proceedings of the 19th International Conference on Artificial Intelligence and Law, 71–80. ACM. [find](https://scholar.google.com/scholar?q=Chen%2C+A%2E%3B+Yao%2C+F%2E%3B+Zhao%2C+X%2E%3B+Zhang%2C+Y%2E%3B+Sun%2C+C%2E%3B+Liu%2C+Y%2E%3B+and+Shen%2C+W%2E+2023a%2E+EQUALS%3A+A+Real%2Dworld+Dataset+for+Legal+Question+Answering+via+Reading+Chinese+Laws%2E+In+Proceedings+of+the+19th+Internation)
14. Chen, D.; Fisch, A.; Weston, J.; and Bordes, A. 2017a. [Reading Wikipedia to Answer Open-Domain Questions](https://md.research.elamur.ai/free/en/papers/chen-2017-reading-wikipedia-answer-open-domain/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 1870–1879. Association for Computational Linguistics.
15. Chen, S.; Wong, S.; Chen, L.; and Tian, Y. 2023b. Extending Context Window of Large Language Models via Positional Interpolation. CoRR, abs/2306.15595. [↗](https://arxiv.org/abs/2306.15595)
16. Chen, T.; Sun, Y.; Shi, Y.; and Hong, L. 2017b. On Sampling Strategies for Neural Network-based Collaborative Filtering. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 767–776. [find](https://scholar.google.com/scholar?q=Chen%2C+T%2E%3B+Sun%2C+Y%2E%3B+Shi%2C+Y%2E%3B+and+Hong%2C+L%2E+2017b%2E+On+Sampling+Strategies+for+Neural+Network%2Dbased+Collaborative+Filtering%2E+In+Proceedings+of+the+23rd+ACM+SIGKDD+International+Conference+on+Knowledge+Dis)
17. Chen, Y.; Song, Z.; Wu, X.; Wang, D.; Xu, J.; Chen, J.; Zhou, H.; and Li, L. 2022. MTG: A Benchmark Suite for Multilingual Text Generation. In Findings of the Association for Computational Linguistics: NAACL 2022, 2508–2527. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Chen%2C+Y%2E%3B+Song%2C+Z%2E%3B+Wu%2C+X%2E%3B+Wang%2C+D%2E%3B+Xu%2C+J%2E%3B+Chen%2C+J%2E%3B+Zhou%2C+H%2E%3B+and+Li%2C+L%2E+2022%2E+MTG%3A+A+Benchmark+Suite+for+Multilingual+Text+Generation%2E+In+Findings+of+the+Association+for+Computational+Linguistics)
18. Chiang, W.-L.; Li, Z.; Lin, Z.; Sheng, Y.; Wu, Z.; Zhang, H.; Zheng, L.; Zhuang, S.; Zhuang, Y.; Gonzalez, J. E.; Stoica, I.; and Xing, E. P. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. [https://lmsys.org/blog/2023-03-30-vicuna/](https://lmsys.org/blog/2023-03-30-vicuna/). [↗](https://lmsys.org/blog/2023-03-30-vicuna/)
19. Currie, A. 2009. The legal problems of everyday life. In Access to justice, 1–41. Emerald Group Publishing Limited. [find](https://scholar.google.com/scholar?q=Currie%2C+A%2E+2009%2E+The+legal+problems+of+everyday+life%2E+In+Access+to+justice%2C+1%E2%80%9341%2E+Emerald+Group+Publishing+Limited%2E)
20. Denvir, C. 2016. Online and in the know? Public legal education, young people and the Internet. Computers & Education, 92-93: 204–220. [find](https://scholar.google.com/scholar?q=Denvir%2C+C%2E+2016%2E+Online+and+in+the+know%3F+Public+legal+education%2C+young+people+and+the+Internet%2E+Computers+%26+Education%2C+92%2D93%3A+204%E2%80%93220%2E)
21. Dettmers, T.; Pagnoni, A.; Holtzman, A.; and Zettlemoyer, L. 2023. [QLoRA: Efficient Finetuning of Quantized LLMs](https://md.research.elamur.ai/free/en/papers/dettmers-2023-qlora-efficient-finetuning-quantized-llms/). CoRR, abs/2305.14314. [↗](https://arxiv.org/abs/2305.14314)
22. Devlin, J.; Chang, M.; Lee, K.; and Toutanova, K. 2019. [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, 4171–4186. Association for Computational Linguistics.
23. Duan, X.; Wang, B.; Wang, Z.; Ma, W.; Cui, Y.; Wu, D.; Wang, S.; Liu, T.; Huo, T.; Hu, Z.; Wang, H.; and Liu, Z. 2019. CJRC: A Reliable Human-Annotated Benchmark Dataset for Chinese Judicial Reading Comprehension. In Proceedings of the 18th China National Conference on Chinese Computational Linguistics, volume 11856 of Lecture Notes in Computer Science, 439–451. Springer. [find](https://scholar.google.com/scholar?q=Duan%2C+X%2E%3B+Wang%2C+B%2E%3B+Wang%2C+Z%2E%3B+Ma%2C+W%2E%3B+Cui%2C+Y%2E%3B+Wu%2C+D%2E%3B+Wang%2C+S%2E%3B+Liu%2C+T%2E%3B+Huo%2C+T%2E%3B+Hu%2C+Z%2E%3B+Wang%2C+H%2E%3B+and+Liu%2C+Z%2E+2019%2E+CJRC%3A+A+Reliable+Human%2DAnnotated+Benchmark+Dataset+for+Chinese+Judicial+Reading+C)
24. Farrow, T. C.; Currie, A.; Aylwin, N.; Jacobs, L.; Northrup, D.; and Moore, L. 2016. Everyday legal problems and the cost of justice in Canada: Overview report. Osgoode Legal Studies Research Paper, 12(57). [find](https://scholar.google.com/scholar?q=Farrow%2C+T%2E+C%2E%3B+Currie%2C+A%2E%3B+Aylwin%2C+N%2E%3B+Jacobs%2C+L%2E%3B+Northrup%2C+D%2E%3B+and+Moore%2C+L%2E+2016%2E+Everyday+legal+problems+and+the+cost+of+justice+in+Canada%3A+Overview+report%2E+Osgoode+Legal+Studies+Research+Paper%2C+1)
25. Garavano, G. C.; Kaag, S.; Schwartz, P.; Jilani, H.; Alvarez, A.; Ardyanto, D.; Goldston, J.; de Greiff, P.; Hossain, S.; Kennou, K.; Maru, V.; Maynard-Gibson, A.; Molokomme, A.; Pell, O.; Pais, M. S.; Rodriguez, M. F.; van Wieren, J.; and Osho, B. 2019. Justice for All: The Report of the Task Force on Justice. Center on International Cooperation. [find](https://scholar.google.com/scholar?q=Garavano%2C+G%2E+C%2E%3B+Kaag%2C+S%2E%3B+Schwartz%2C+P%2E%3B+Jilani%2C+H%2E%3B+Alvarez%2C+A%2E%3B+Ardyanto%2C+D%2E%3B+Goldston%2C+J%2E%3B+de+Greiff%2C+P%2E%3B+Hossain%2C+S%2E%3B+Kennou%2C+K%2E%3B+Maru%2C+V%2E%3B+Maynard%2DGibson%2C+A%2E%3B+Molokomme%2C+A%2E%3B+Pell%2C+O%2E%3B+Pais%2C+M%2E+S%2E)
26. Hagan, M.; and Li, Y. 2020. Legal Help Search Audit: Are Search Engines Effective Brokers of Legal Information? Available at SSRN 3623333. [find](https://scholar.google.com/scholar?q=Hagan%2C+M%2E%3B+and+Li%2C+Y%2E+2020%2E+Legal+Help+Search+Audit%3A+Are+Search+Engines+Effective+Brokers+of+Legal+Information%3F+Available+at+SSRN+3623333%2E)
27. Henderson, M. L.; Al-Rfou, R.; Strope, B.; Sung, Y.; Lukács, L.; Guo, R.; Kumar, S.; Miklos, B.; and Kurzweil, R. 2017. Efficient Natural Language Response Suggestion for Smart Reply. CoRR, abs/1705.00652. [↗](https://arxiv.org/abs/1705.00652)
28. Holland, S.; Hosny, A.; Newman, S.; Joseph, J.; and Chmielinski, K. 2018. The Dataset Nutrition Label: A Framework To Drive Higher Data Quality Standards. CoRR, abs/1805.03677. [↗](https://arxiv.org/abs/1805.03677)
29. Holtzman, A.; Buys, J.; Du, L.; Forbes, M.; and Choi, Y. 2020. [The Curious Case of Neural Text Degeneration](https://md.research.elamur.ai/free/en/papers/holtzman-2019-curious-case-neural-text-degeneration/). In Proceedings of the 8th International Conference on Learning Representations. OpenReview.net.
30. Holzenberger, N.; Blair-Stanek, A.; and Durme, B. V. 2020. [A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering](https://md.research.elamur.ai/free/en/papers/holzenberger-2020-dataset-statutory-reasoning-tax-law/). In Proceedings of the Natural Legal Language Processing Workshop 2020 co-located with the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, volume 2645 of CEUR Workshop Proceedings, 31–38.
31. CEUR-WS.org. Hu, E. J.; Shen, Y.; Wallis, P.; Allen-Zhu, Z.; Li, Y.; Wang, S.; Wang, L.; and Chen, W. 2022. [LoRA: Low-Rank Adaptation of Large Language Models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In Proceedings of the 10th International Conference on Learning Representations.
32. OpenReview.net. Ishigaki, T.; Huang, H.; Takamura, H.; Chen, H.; and Okumura, M. 2020. Neural Query-Biased Abstractive Summarization Using Copying Mechanism. In Advances in Information Retrieval - 42nd European Conference on IR Research, volume 12036 of Lecture Notes in Computer Science, 174–181. Springer. [find](https://scholar.google.com/scholar?q=OpenReview%2Enet%2E+Ishigaki%2C+T%2E%3B+Huang%2C+H%2E%3B+Takamura%2C+H%2E%3B+Chen%2C+H%2E%3B+and+Okumura%2C+M%2E+2020%2E+Neural+Query%2DBiased+Abstractive+Summarization+Using+Copying+Mechanism%2E+In+Advances+in+Information+Retrieval+%2D+42n)
33. Jacot, A.; Hongler, C.; and Gabriel, F. 2018. Neural Tangent Kernel: Convergence and Generalization in Neural Networks. In Advances in Neural Information Processing Systems, volume 31, 8580–8589. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Jacot%2C+A%2E%3B+Hongler%2C+C%2E%3B+and+Gabriel%2C+F%2E+2018%2E+Neural+Tangent+Kernel%3A+Convergence+and+Generalization+in+Neural+Networks%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+31%2C+8580%E2%80%938589%2E+Curr)
34. Ji, Z.; Lee, N.; Frieske, R.; Yu, T.; Su, D.; Xu, Y.; Ishii, E.; Bang, Y.; Madotto, A.; and Fung, P. 2023. [Survey of Hallucination in Natural Language Generation](https://md.research.elamur.ai/free/en/papers/ji-2022-survey-hallucination-natural-language-generation/). ACM Computing Surveys, 55(12): 248:1–248:38.
35. Karpukhin, V.; Oguz, B.; Min, S.; Lewis, P. S. H.; Wu, L.; Edunov, S.; Chen, D.; and Yih, W. 2020. [Dense Passage Retrieval for Open-Domain Question Answering](https://md.research.elamur.ai/free/en/papers/karpukhin-2020-dense-passage-retrieval-open-domain/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processin, 6769–6781. Association for Computational Linguistics.
36. Krishna, K.; Roy, A.; and Iyyer, M. 2021. [Hurdles to Progress in Long-form Question Answering](https://md.research.elamur.ai/free/en/papers/krishna-2021-hurdles-progress-long-form-question/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 4940–4957. Association for Computational Linguistics.
37. Kumar, S.; and Talukdar, P. P. 2020. [NILE : Natural Language Inference with Faithful Natural Language Explanations](https://md.research.elamur.ai/free/en/papers/kumar-2020-nile-natural-language-inference-faithful/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 8730–8742. Association for Computational Linguistics.
38. Kwok, C. C. T.; Etzioni, O.; and Weld, D. S. 2001. Scaling question answering to the web. ACM Transactions on Information Systems, 19(3): 242–262. [find](https://scholar.google.com/scholar?q=Kwok%2C+C%2E+C%2E+T%2E%3B+Etzioni%2C+O%2E%3B+and+Weld%2C+D%2E+S%2E+2001%2E+Scaling+question+answering+to+the+web%2E+ACM+Transactions+on+Information+Systems%2C+19%283%29%3A+242%E2%80%93262%2E)
39. Lakhotia, K.; Paranjape, B.; Ghoshal, A.; Yih, S.; Mehdad, Y.; and Iyer, S. 2021. FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 3712–3727. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Lakhotia%2C+K%2E%3B+Paranjape%2C+B%2E%3B+Ghoshal%2C+A%2E%3B+Yih%2C+S%2E%3B+Mehdad%2C+Y%2E%3B+and+Iyer%2C+S%2E+2021%2E+FiD%2DEx%3A+Improving+Sequence%2Dto%2DSequence+Models+for+Extractive+Rationale+Generation%2E+In+Proceedings+of+the+2021+Conferen)
40. Latcinnik, V.; and Berant, J. 2020. Explaining Question Answering Models through Text Generation. CoRR, abs/2004.05569. [↗](https://arxiv.org/abs/2004.05569)
41. Lee, K.; Chang, M.; and Toutanova, K. 2019. [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://md.research.elamur.ai/free/en/papers/lee-2019-latent-retrieval-weakly-supervised-open/). In Proceedings of the 57th Conference of the Association for Computational Linguistic, 6086–6096. Association for Computational Linguistics.
42. Lei, T.; Barzilay, R.; and Jaakkola, T. S. 2016. [Rationalizing Neural Predictions](https://md.research.elamur.ai/free/en/papers/lei-2016-rationalizing-neural-predictions/). In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 107–117. The Association for Computational Linguistics.
43. Lester, B.; Al-Rfou, R.; and Constant, N. 2021. [The Power of Scale for Parameter-Efficient Prompt Tuning](https://md.research.elamur.ai/free/en/papers/lester-2021-power-scale-parameter-efficient-prompt/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 3045–3059. Association for Computational Linguistics.
44. Lin, C.-Y. 2004. [ROUGE: A Package for Automatic Evaluation of Summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/)”. In Text Summarization Branches Out, 74–81. Association for Computational Linguistics.
45. Litvak, M.; and Vanetik, N. 2017. Query-based summarization using MDL principle. In Proceedings of the Workshop on Summarization and Summary Evaluation Across Source Types and Genres, MultiLing@EACL 2017, 22–31. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Litvak%2C+M%2E%3B+and+Vanetik%2C+N%2E+2017%2E+Query%2Dbased+summarization+using+MDL+principle%2E+In+Proceedings+of+the+Workshop+on+Summarization+and+Summary+Evaluation+Across+Source+Types+and+Genres%2C+MultiLing%40EACL+2)
46. Liu, X.; Ji, K.; Fu, Y.; Tam, W.; Du, Z.; Yang, Z.; and Tang, J. 2022. [P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks](https://md.research.elamur.ai/free/en/papers/liu-2022-p-tuning-prompt-tuning-can/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 61–68. Association for Computational Linguistics.
47. Loshchilov, I.; and Hutter, F. 2017. Decoupled Weight Decay Regularization. In Proceedings of the 7th International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Loshchilov%2C+I%2E%3B+and+Hutter%2C+F%2E+2017%2E+Decoupled+Weight+Decay+Regularization%2E+In+Proceedings+of+the+7th+International+Conference+on+Learning+Representations%2E)
48. Louis, A.; and Spanakis, G. 2022. A Statutory Article Retrieval Dataset in French. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 6789–6803. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Louis%2C+A%2E%3B+and+Spanakis%2C+G%2E+2022%2E+A+Statutory+Article+Retrieval+Dataset+in+French%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C+6)
49. Mangrulkar, S.; Gugger, S.; Debut, L.; Belkada, Y.; and Paul, S. 2022. PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. [https://github.com/huggingface/peft](https://github.com/huggingface/peft). [↗](https://github.com/huggingface/peft)
50. Mansouri, B.; and Campos, R. 2023. FALQU: Finding Answers to Legal Questions. In Proceedings of the 1st International Workshop on Legal Information Retrieval co-located with the 45th European Conference on Information Retrieval, 22–24. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Mansouri%2C+B%2E%3B+and+Campos%2C+R%2E+2023%2E+FALQU%3A+Finding+Answers+to+Legal+Questions%2E+In+Proceedings+of+the+1st+International+Workshop+on+Legal+Information+Retrieval+co%2Dlocated+with+the+45th+European+Conferen)
51. Martin, L.; Müller, B.; Suárez, P. J. O.; Dupont, Y.; Romary, L.; de la Clergerie, É.; Seddah, D.; and Sagot, B. 2020. [CamemBERT: a Tasty French Language Model](https://md.research.elamur.ai/free/en/papers/martin-2019-camembert-tasty-french-language-model/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, 7203–7219. Association for Computational Linguistics.
52. Min, S.; Lyu, X.; Holtzman, A.; Artetxe, M.; Lewis, M.; Hajishirzi, H.; and Zettlemoyer, L. 2022. [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://md.research.elamur.ai/free/en/papers/min-2022-rethinking-role-demonstrations-what-makes/) In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 11048–11064. Association for Computational Linguistics.
53. Muennighoff, N.; Tazi, N.; Magne, L.; and Reimers, N. 2023. [MTEB: Massive Text Embedding Benchmark](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-mteb-massive-text-embedding-benchmark/). In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2006–2029. Association for Computational Linguistics.
54. Murdoch, W. J.; Liu, P. J.; and Yu, B. 2018. Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs. In Proceedings of the 6th International Conference on Learning Representations. OpenReview.net. [find](https://scholar.google.com/scholar?q=Murdoch%2C+W%2E+J%2E%3B+Liu%2C+P%2E+J%2E%3B+and+Yu%2C+B%2E+2018%2E+Beyond+Word+Importance%3A+Contextual+Decomposition+to+Extract+Interactions+from+LSTMs%2E+In+Proceedings+of+the+6th+International+Conference+on+Learning+Represe)
55. Narang, S.; Raffel, C.; Lee, K.; Roberts, A.; Fiedel, N.; and Malkan, K. 2020. [WT5?! Training Text-to-Text Models to Explain their Predictions](https://md.research.elamur.ai/free/en/papers/narang-2020-wt5-training-text-text-models/). CoRR, abs/2004.14546. [↗](https://arxiv.org/abs/2004.14546)
56. Nema, P.; Khapra, M. M.; Laha, A.; and Ravindran, B. 2017. Diversity driven attention model for query-based abstractive summarization. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 1063– 1072. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Nema%2C+P%2E%3B+Khapra%2C+M%2E+M%2E%3B+Laha%2C+A%2E%3B+and+Ravindran%2C+B%2E+2017%2E+Diversity+driven+attention+model+for+query%2Dbased+abstractive+summarization%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+)
57. Otterbacher, J.; Erkan, G.; and Radev, D. R. 2009. Biased LexRank: Passage retrieval using random walks with question-based priors. Information Processing and Management, 45(1): 42–54. [find](https://scholar.google.com/scholar?q=Otterbacher%2C+J%2E%3B+Erkan%2C+G%2E%3B+and+Radev%2C+D%2E+R%2E+2009%2E+Biased+LexRank%3A+Passage+retrieval+using+random+walks+with+question%2Dbased+priors%2E+Information+Processing+and+Management%2C+45%281%29%3A+42%E2%80%9354%2E)
58. Paranjape, B.; Joshi, M.; Thickstun, J.; Hajishirzi, H.; and Zettlemoyer, L. 2020. [An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction](https://md.research.elamur.ai/free/en/papers/paranjape-2020-information-bottleneck-approach-controlling-conciseness/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 1938–1952. Association for Computational Linguistics.
59. Ponce, A.; Chamness Long, S.; Andersen, E.; Gutierrez Patino, C.; Harman, M.; A Morales, J.; Piccone, T.; Rodriguez Cajamarca, N.; Stephan, A.; Gonzalez, K.; Van-Riper, J.; Evangelides, A.; Martin, R.; Khosla, P.; Bock, L.; Campbell, E.; Gray, E.; Gryskiewicz, A.; Ibrahim, A.; Solis, L.; Hearn-Desautels, G.; and Tinucci, F. 2019. Global Insights on Access to Justice 2019: Findings from the World Justice Project General Population Poll in 101 Countries. World Justice Project. [find](https://scholar.google.com/scholar?q=Ponce%2C+A%2E%3B+Chamness+Long%2C+S%2E%3B+Andersen%2C+E%2E%3B+Gutierrez+Patino%2C+C%2E%3B+Harman%2C+M%2E%3B+A+Morales%2C+J%2E%3B+Piccone%2C+T%2E%3B+Rodriguez+Cajamarca%2C+N%2E%3B+Stephan%2C+A%2E%3B+Gonzalez%2C+K%2E%3B+Van%2DRiper%2C+J%2E%3B+Evangelides%2C+A%2E%3B+Martin%2C+R%2E)
60. Rabelo, J.; Goebel, R.; Kim, M.; Kano, Y.; Yoshioka, M.; and Satoh, K. 2022. Overview and Discussion of the Competition on Legal Information Extraction/Entailment (COL-IEE) 2021. The Review of Socionetwork Strategies, 16(1): 111–133. [find](https://scholar.google.com/scholar?q=Rabelo%2C+J%2E%3B+Goebel%2C+R%2E%3B+Kim%2C+M%2E%3B+Kano%2C+Y%2E%3B+Yoshioka%2C+M%2E%3B+and+Satoh%2C+K%2E+2022%2E+Overview+and+Discussion+of+the+Competition+on+Legal+Information+Extraction%2FEntailment+%28COL%2DIEE%29+2021%2E+The+Review+of+Socione)
61. Radford, A.; Wu, J.; Child, R.; Luan, D.; Amodei, D.; Sutskever, I.; et al. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8): 9. [find](https://scholar.google.com/scholar?q=Radford%2C+A%2E%3B+Wu%2C+J%2E%3B+Child%2C+R%2E%3B+Luan%2C+D%2E%3B+Amodei%2C+D%2E%3B+Sutskever%2C+I%2E%3B+et+al%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A+9%2E)
62. Rajani, N. F.; McCann, B.; Xiong, C.; and Socher, R. 2019. [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://md.research.elamur.ai/free/en/papers/rajani-2019-explain-yourself-leveraging-language-models/). In Proceedings of the 57th Conference of the Association for Computational Linguistics, 4932–4942. Association for Computational Linguistics.
63. Ravichander, A.; Black, A. W.; Wilson, S.; Norton, T. B.; and Sadeh, N. M. 2019. [Question Answering for Privacy Policies: Combining Computational and Legal Perspectives](https://md.research.elamur.ai/free/en/papers/ravichander-2019-question-answering-privacy-policies-combining/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, 4946–4957. Association for Computational Linguistics.
64. Reimers, N.; and Gurevych, I. 2019. [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 3980– 3990. Association for Computational Linguistics.
65. Ribeiro, M. T.; Singh, S.; and Guestrin, C. 2016. [”Why Should I Trust You?”: Explaining the Predictions of Any Classifier](https://md.research.elamur.ai/free/en/papers/ribeiro-2016-why-should-i-trust-explaining/). In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135–1144. ACM.
66. Roberts, A.; Raffel, C.; and Shazeer, N. 2020. How Much Knowledge Can You Pack Into the Parameters of a Language Model? In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 5418–5426. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Roberts%2C+A%2E%3B+Raffel%2C+C%2E%3B+and+Shazeer%2C+N%2E+2020%2E+How+Much+Knowledge+Can+You+Pack+Into+the+Parameters+of+a+Language+Model%3F+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Language+P)
67. Robertson, S. E.; Walker, S.; Jones, S.; Hancock-Beaulieu, M.; and Gatford, M. 1994. [Okapi at TREC-3](https://md.research.elamur.ai/free/en/papers/robertson-1994-okapi-trec-3/). In Proceedings of The Third Text REtrieval Conference, volume 500-225 of NIST Special Publication, 109–126. National Institute of Standards and Technology.
68. Sharma, S.; Asri, L. E.; Schulz, H.; and Zumer, J. 2017. Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation. CoRR, abs/1706.09799. [↗](https://arxiv.org/abs/1706.09799)
69. Shukla, A.; Bhattacharya, P.; Poddar, S.; Mukherjee, R.; Ghosh, K.; Goyal, P.; and Ghosh, S. 2022. Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing, 1048–1064. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Shukla%2C+A%2E%3B+Bhattacharya%2C+P%2E%3B+Poddar%2C+S%2E%3B+Mukherjee%2C+R%2E%3B+Ghosh%2C+K%2E%3B+Goyal%2C+P%2E%3B+and+Ghosh%2C+S%2E+2022%2E+Legal+Case+Document+Summarization%3A+Extractive+and+Abstractive+Methods+and+their+Evaluation%2E+In+Procee)
70. Su, J.; Lu, Y.; Pan, S.; Wen, B.; and Liu, Y. 2021. [Ro-Former: Enhanced Transformer with Rotary Position Embedding](https://md.research.elamur.ai/free/en/papers/su-2021-roformer-enhanced-transformer-rotary-position/). CoRR, abs/2104.09864. [↗](https://arxiv.org/abs/2104.09864)
71. Tombros, A.; and Sanderson, M. 1998. Advantages of Query Biased Summaries in Information Retrieval. In SIGIR ’98: Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2–10. ACM. [find](https://scholar.google.com/scholar?q=Tombros%2C+A%2E%3B+and+Sanderson%2C+M%2E+1998%2E+Advantages+of+Query+Biased+Summaries+in+Information+Retrieval%2E+In+SIGIR+%E2%80%9998%3A+Proceedings+of+the+21st+Annual+International+ACM+SIGIR+Conference+on+Research+and+Deve)
72. Touvron, H.; Lavril, T.; Izacard, G.; Martinet, X.; Lachaux, M.; Lacroix, T.; Rozière, B.; Goyal, N.; Hambro, E.; Azhar, F.; Rodriguez, A.; Joulin, A.; Grave, E.; and Lample, G. 2023. [LLaMA: Open and Efficient Foundation Language Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). CoRR, abs/2302.13971. [↗](https://arxiv.org/abs/2302.13971)
73. Trautmann, D.; Petrova, A.; and Schilder, F. 2022. Legal Prompt Engineering for Multilingual Legal Judgement Prediction. CoRR, abs/2212.02199. [↗](https://arxiv.org/abs/2212.02199)
74. Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, L.; and Polosukhin, I. 2017. [Attention is All you Need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in Neural Information Processing Systems, volume 30, 5998–6008. Curran Associates, Inc.
75. Voorhees, E. M. 1999. [The TREC-8 Question Answering Track](https://md.research.elamur.ai/free/en/papers/voorhees-2000-trec-8-question-answering-track/) Report. In Proceedings of The Eighth Text REtrieval Conference, volume 500-246 of NIST Special Publication. National Institute of Standards and Technology (NIST).
76. Wang, L.; Raghavan, H.; Castelli, V.; Florian, R.; and Cardie, C. 2013. A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, 1384–1394. The Association for Computer Linguistics. [find](https://scholar.google.com/scholar?q=Wang%2C+L%2E%3B+Raghavan%2C+H%2E%3B+Castelli%2C+V%2E%3B+Florian%2C+R%2E%3B+and+Cardie%2C+C%2E+2013%2E+A+Sentence+Compression+Based+Framework+to+Query%2DFocused+Multi%2DDocument+Summarization%2E+In+Proceedings+of+the+51st+Annual+Meeting+)
77. Wang, L.; Yang, N.; Huang, X.; Jiao, B.; Yang, L.; Jiang, D.; Majumder, R.; and Wei, F. 2022a. [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://md.research.elamur.ai/free/en/papers/wang-2022-text-embeddings-weakly-supervised-contrastive/). CoRR, abs/2212.03533. [↗](https://arxiv.org/abs/2212.03533)
78. Wang, S.; Xu, F.; Thompson, L.; Choi, E.; and Iyyer, M. 2022b. Modeling Exemplification in Long-form Question Answering via Retrieval. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2079–2092. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Wang%2C+S%2E%3B+Xu%2C+F%2E%3B+Thompson%2C+L%2E%3B+Choi%2C+E%2E%3B+and+Iyyer%2C+M%2E+2022b%2E+Modeling+Exemplification+in+Long%2Dform+Question+Answering+via+Retrieval%2E+In+Proceedings+of+the+2022+Conference+of+the+North+American+Chapt)
79. Wang, Y.; Ivison, H.; Dasigi, P.; Hessel, J.; Khot, T.; Chandu, K. R.; Wadden, D.; MacMillan, K.; Smith, N. A.; Beltagy, I.; and Hajishirzi, H. 2023. [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://md.research.elamur.ai/free/en/papers/wang-2023-far-camels-go-exploring-state/). CoRR, abs/2306.04751. [↗](https://arxiv.org/abs/2306.04751)
80. Wiegreffe, S.; Marasovic, A.; and Smith, N. A. 2021. [Measuring Association Between Labels and Free-Text Rationales](https://md.research.elamur.ai/free/en/papers/wiegreffe-2021-measuring-association-between-labels-free/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 10266–10284. Association for Computational Linguistics.
81. Wolf, T.; Debut, L.; Sanh, V.; Chaumond, J.; Delangue, C.; Moi, A.; Cistac, P.; Rault, T.; Louf, R.; Funtowicz, M.; Davison, J.; Shleifer, S.; von Platen, P.; Ma, C.; Jernite, Y.; Plu, J.; Xu, C.; Scao, T. L.; Gugger, S.; Drame, M.; Lhoest, Q.; and Rush, A. M. 2020. [Transformers: State-of-the-Art Natural Language Processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 38–45. Association for Computational Linguistics.
82. Xiong, L.; Xiong, C.; Li, Y.; Tang, K.; Liu, J.; Bennett, P. N.; Ahmed, J.; and Overwijk, A. 2021. [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://md.research.elamur.ai/free/en/papers/xiong-2020-approximate-nearest-neighbor-negative-contrastive/). In Proceedings of the 9th International Conference on Learning Representations.
83. OpenReview.net. Xu, C.; Sun, Q.; Zheng, K.; Geng, X.; Zhao, P.; Feng, J.; Tao, C.; and Jiang, D. 2023a. [WizardLM: Empowering Large Language Models to Follow Complex Instructions](https://md.research.elamur.ai/free/en/papers/xu-2023-wizardlm-empowering-large-pre-trained/). CoRR, abs/2304.12244. [↗](https://arxiv.org/abs/2304.12244)
84. Xu, F.; Song, Y.; Iyyer, M.; and Choi, E. 2023b. [A Critical Evaluation of Evaluations for Long-form Question Answering](https://md.research.elamur.ai/free/en/papers/xu-2023-critical-evaluation-evaluations-long-form/). In Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 3225–3245. Association for Computational Linguistics.
85. Yang, Y.; Cer, D.; Ahmad, A.; Guo, M.; Law, J.; Constant, N.; Ábrego, G. H.; Yuan, S.; Tar, C.; Sung, Y.; Strope, B.; and Kurzweil, R. 2020. [Multilingual Universal Sentence Encoder for Semantic Retrieval](https://md.research.elamur.ai/free/en/papers/yang-2020-multilingual-universal-sentence-encoder-semantic/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 87–94. Association for Computational Linguistics.
86. Yu, M.; Yin, W.; Hasan, K. S.; dos Santos, C. N.; Xiang, B.; and Zhou, B. 2017. Improved Neural Relation Detection for Knowledge Base Question Answering. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 571–581. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yu%2C+M%2E%3B+Yin%2C+W%2E%3B+Hasan%2C+K%2E+S%2E%3B+dos+Santos%2C+C%2E+N%2E%3B+Xiang%2C+B%2E%3B+and+Zhou%2C+B%2E+2017%2E+Improved+Neural+Relation+Detection+for+Knowledge+Base+Question+Answering%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+t)
87. Zheng, L.; Chiang, W.; Sheng, Y.; Zhuang, S.; Wu, Z.; Zhuang, Y.; Lin, Z.; Li, Z.; Li, D.; Xing, E. P.; Zhang, H.; Gonzalez, J. E.; and Stoica, I. 2023. [Judging LLM-as-a-judge with MT-Bench and Chatbot Arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). CoRR, abs/2306.05685. [↗](https://arxiv.org/abs/2306.05685)
88. Zhong, H.; Xiao, C.; Tu, C.; Zhang, T.; Liu, Z.; and Sun, M. 2020. JEC-QA: A Legal-Domain Question Answering Dataset. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, 9701–9708. AAAI Press. [find](https://scholar.google.com/scholar?q=Zhong%2C+H%2E%3B+Xiao%2C+C%2E%3B+Tu%2C+C%2E%3B+Zhang%2C+T%2E%3B+Liu%2C+Z%2E%3B+and+Sun%2C+M%2E+2020%2E+JEC%2DQA%3A+A+Legal%2DDomain+Question+Answering+Dataset%2E+In+The+Thirty%2DFourth+AAAI+Conference+on+Artificial+Intelligence%2C+9701%E2%80%939708%2E+AAAI+P)

*Updated 2 November 2026*