---
title: "SAIL: Search-Augmented Instruction Learning (2023)"
description: "The work offers an academic-budget recipe for grounding on noisy, real-world search engines instead… 39 references, cited by 38 papers here."
authors: ["Hongyin Luo", "Yung-Sung Chuang", "Yuan Gong", "Tianhua Zhang", "Yoon Kim", "Xixin Wu", "Danny Fox", "Helen Meng", "James Glass"]
year: 2023
venue: "arXiv:2305.15225"
source: "https://arxiv.org/abs/2305.15225"
doi: "10.48550/arxiv.2305.15225"
arxiv: "2305.15225"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/luo-2023-sail-search-augmented-instruction-learning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/luo-2023-sail-search-augmented-instruction-learning/)

[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/11/) / SAIL: Search-Augmented Instruction Learning

# SAIL: Search-Augmented Instruction Learning

**Authors:** [Hongyin Luo](https://md.research.elamur.ai/free/en/authors/hongyin-luo/), [Yung-Sung Chuang](https://md.research.elamur.ai/free/en/authors/yung-sung-chuang/), [Yuan Gong](https://md.research.elamur.ai/free/en/authors/yuan-gong/), [Tianhua Zhang](https://md.research.elamur.ai/free/en/authors/tianhua-zhang/), [Yoon Kim](https://md.research.elamur.ai/free/en/authors/yoon-kim/), [Xixin Wu](https://md.research.elamur.ai/free/en/authors/xixin-wu/), [Danny Fox](https://md.research.elamur.ai/free/en/authors/danny-fox/), [Helen Meng](https://md.research.elamur.ai/free/en/authors/helen-meng/) and [James Glass](https://md.research.elamur.ai/free/en/authors/james-glass/) · **Year:** 2023 · **Venue:** arXiv:2305.15225 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2305.15225) · [PDF](https://arxiv.org/pdf/2305.15225) · [DOI 10.48550/arxiv.2305.15225](https://doi.org/10.48550/arxiv.2305.15225) · [arXiv 2305.15225](https://arxiv.org/abs/2305.15225) · [OpenAlex](https://openalex.org/W4378474184)

**Citations:** 5 citations (OpenAlex, 2026-10-14) · [38](https://md.research.elamur.ai/free/en/papers/luo-2023-sail-search-augmented-instruction-learning/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Instruction-tuned LLMs rely on knowledge frozen at training time and give answers that cannot be traced to sources. Attaching web search results can help, but irrelevant or contradictory hits often mislead them, and the authors show even GPT-3.5-Turbo can be misled this way. SAIL teaches a model to sort retrieved evidence before answering. The authors start from the 52k Alpaca instructions paired with GPT-4 responses. They attach to each example a random subset of results from DuckDuckGo and a BM25 Wikipedia retriever, producing (instruction, grounding information, response) triplets. An entailment classifier labels each passage as informative or distracting relative to the target answer. These labels become an explicit selection statement that the model writes before its response. Fine-tuning LLaMA-7B on this corpus yields SAIL-7B. It follows instructions well and, according to the authors, outperforms GPT-3.5-Turbo and Vicuna-13B on several tasks, notably open-ended QA and fact/fairness checking. The work offers an academic-budget recipe for grounding on noisy, real-world search engines instead of a curated static knowledge base.

## Key points
- **Training data:** The corpus builds on the Alpaca 52k self-instruct set with GPT-4 responses.
  - Search queries are the instruction plus the input, capped at 60 words.
  - Each result keeps only its title and preview snippet; pages are not scraped.
- **Search sampling:** Results come from a pool of five passages, three from DuckDuckGo and two from BM25 Wikipedia. Each example receives 0, 1, 2 or 3 of them with probabilities of 20/20/20/40%.
- **Passage labeling:** Each passage is labeled automatically with the entailment model of Luo and Glass (2023). A passage counts as informative when its entailment score exceeds its contradiction score; otherwise it counts as distracting.
- **Training setup:** SAIL-7B was trained on 4× NVIDIA RTX A6000 GPUs for 3 epochs, which took about 24 hours.
  - Settings: fp16, AdamW, max sequence length 1,600, batch size 32.
  - Memory was managed with gradient checkpointing, DeepSpeed offload and FSDP.
- **Comparisons and limitations:** SAIL-7B was compared against LLaMA-7B, Vicuna-7B, Vicuna-13B and GPT-3.5-Turbo. A stated limitation is that the model does not explain why it judges a search result trustworthy.

*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

- [Massachusetts Institute of Technology](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) — University, Cambridge, United States · 274 works · 82,013 citations
- [MIT Computer Science and Artificial Intelligence Laboratory](https://md.research.elamur.ai/free/en/labs/mit-computer-science-and-artificial-intelligence-laboratory/) — Research institute, Cambridge, United States · 80 works · 32,402 citations
- [Chinese University of Hong Kong](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/) — University, Hong Kong, China · 176 works · 17,536 citations
- [Centre for Perceptual and Interactive Intelligence](https://md.research.elamur.ai/free/en/labs/centre-for-perceptual-and-interactive-intelligence/) — Research institute, Hong Kong, China · 9 works · 1,252 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,888 works

## Cite

Cite as: Hongyin Luo, Yung-Sung Chuang, Yuan Gong, Tianhua Zhang, Yoon Kim, Xixin Wu, Danny Fox, Helen Meng and James Glass. 2023. SAIL: Search-Augmented Instruction Learning. arXiv:2305.15225.

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

```bibtex
@misc{luo2023sail,
  title = {{SAIL: Search-Augmented Instruction Learning}},
  author = {Hongyin Luo, Yung-Sung Chuang, Yuan Gong, Tianhua Zhang, Yoon Kim, Xixin Wu, Danny Fox, Helen Meng and James Glass},
  year = {2023},
  doi = {10.48550/arxiv.2305.15225},
  eprint = {2305.15225},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2305.15225}
}
```

- [← previous Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages](https://md.research.elamur.ai/free/en/papers/hu-2023-large-multilingual-models-pivot-zero/)
- [next → ZeroShotDataAug: Generating and Augmenting Training Data with ChatGPT](https://md.research.elamur.ai/free/en/papers/ubani-2023-zeroshotdataaug-generating-augmenting-training-data/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/11/)

## References

39 references, 30 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al. 2022. Improving language models by retrieving from trillions of tokens. In International conference on machine learn… [find](https://scholar.google.com/scholar?q=Sebastian+Borgeaud%2C+Arthur+Mensch%2C+Jordan+Hoffmann%2C+Trevor+Cai%2C+Eliza+Rutherford%2C+Katie+Millican%2C+George+Bm+Van+Den+Driessche%2C+Jean%2DBaptiste+Lespiau%2C+Bogdan+Damoc%2C+Aidan+Clark%2C+et+al%2E+2022%2E+Improving+)
2. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chri… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
3. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020b. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
4. Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes. 2017. [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 (Volume 1: Long Papers), pages 1870–1879.
5. Ona de Gibert, Naiara Perez, Aitor Garcıa-Pablos, and Montse Cuadros. 2018. [Hate speech dataset from a white supremacy forum](https://md.research.elamur.ai/free/en/papers/gibert-2018-hate-speech-dataset-white-supremacy/).
6. Thomas Diggelmann, Jordan Boyd-Graber, Jannis Bulian, Massimiliano Ciaramita, and Markus Leippold. 2020. [Climate-fever: A dataset for verification of real-world climate claims](https://md.research.elamur.ai/free/en/papers/diggelmann-2020-climate-fever-dataset-verification-real/). arXiv preprint arXiv:2012.00614.
7. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. [Retrieval augmented language model pre-training](https://md.research.elamur.ai/free/en/papers/guu-2020-realm-retrieval-augmented-language-model/). In International conference on machine learning, pages 3929–3938. PMLR.
8. Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, and Ece Kamar. 2022. [Toxigen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection](https://md.research.elamur.ai/free/en/papers/hartvigsen-2022-toxigen-large-scale-machine-generated/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1:…
9. Jiaxin Huang, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han. 2022. [Large language models can self-improve](https://md.research.elamur.ai/free/en/papers/huang-2023-large-language-models-can-self/). arXiv preprint arXiv:2210.11610.
10. Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2022. [Few-shot learning with retrieval augmented language models](https://md.research.elamur.ai/free/en/papers/izacard-2022-atlas-few-shot-learning-retrieval/). arXiv preprint arXiv:2208.03299.
11. Neema Kotonya and Francesca Toni. 2020. [Explainable automated fact-checking for public health claims](https://md.research.elamur.ai/free/en/papers/kotonya-2020-explainable-automated-fact-checking-public/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7740–7754, Online. Association for Computational Linguistics.
12. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Red-field, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, et al. 2019. [Natural questions: A benchmark for question answering research](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/). Transactions of the Association for Computational Linguisti…
13. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in Neural Information Processing Systems, 33:9459–9474.
14. Hongyin Luo and James Glass. 2023. Logic against bias: Textual entailment mitigates stereotypical sentence reasoning. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1243–1254, Dubrovnik, Croatia. Association for Computational Lin… [find](https://scholar.google.com/scholar?q=Hongyin+Luo+and+James+Glass%2E+2023%2E+Logic+against+bias%3A+Textual+entailment+mitigates+stereotypical+sentence+reasoning%2E+In+Proceedings+of+the+17th+Conference+of+the+European+Chapter+of+the+Association+f)
15. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al. 2023. Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651. [find](https://scholar.google.com/scholar?q=Aman+Madaan%2C+Niket+Tandon%2C+Prakhar+Gupta%2C+Skyler+Hallinan%2C+Luyu+Gao%2C+Sarah+Wiegreffe%2C+Uri+Alon%2C+Nouha+Dziri%2C+Shrimai+Prabhumoye%2C+Yiming+Yang%2C+et+al%2E+2023%2E+Self%2Drefine%3A+Iterative+refinement+with+self%2Df)
16. Potsawee Manakul, Adian Liusie, and Mark JF Gales. 2023. Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. arXiv preprint arXiv:2303.08896. [find](https://scholar.google.com/scholar?q=Potsawee+Manakul%2C+Adian+Liusie%2C+and+Mark+JF+Gales%2E+2023%2E+Selfcheckgpt%3A+Zero%2Dresource+black%2Dbox+hallucination+detection+for+generative+large+language+models%2E+arXiv+preprint+arXiv%3A2303%2E08896%2E)
17. Todor Mihaylov, Peter Clark, Tushar Khot, and Ashish Sabharwal. 2018. Can a suit of armor conduct electricity? a new dataset for open book question answering. In Conference on Empirical Methods in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Todor+Mihaylov%2C+Peter+Clark%2C+Tushar+Khot%2C+and+Ashish+Sabharwal%2E+2018%2E+Can+a+suit+of+armor+conduct+electricity%3F+a+new+dataset+for+open+book+question+answering%2E+In+Conference+on+Empirical+Methods+in+Nat)
18. Swaroop Mishra, Daniel Khashabi, Chitta Baral, and Hannaneh Hajishirzi. 2022. Cross-task generalization via natural language crowdsourcing instructions. In ACL. [find](https://scholar.google.com/scholar?q=Swaroop+Mishra%2C+Daniel+Khashabi%2C+Chitta+Baral%2C+and+Hannaneh+Hajishirzi%2E+2022%2E+Cross%2Dtask+generalization+via+natural+language+crowdsourcing+instructions%2E+In+ACL%2E)
19. OpenAI. 2022. Introducing chatgpt. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2022%2E+Introducing+chatgpt%2E)
20. OpenAI. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/).
21. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in Neural Information Processing Systems, 35:27730–27744.
22. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. [Pytorch: An imperative style, high-performance deep learning library](https://md.research.elamur.ai/free/en/papers/paszke-2019-pytorch-imperative-style-high-performance/). Advances in neural information processing systems, 32.
23. Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, and Jianfeng Gao. 2023. [Instruction tuning with gpt-4](https://md.research.elamur.ai/free/en/papers/peng-2023-instruction-tuning-gpt-4/). arXiv preprint arXiv:2304.03277.
24. Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. [In-context retrieval-augmented language models](https://md.research.elamur.ai/free/en/papers/ram-2023-context-retrieval-augmented-language-models/). arXiv preprint arXiv:2302.00083.
25. Maarten Sap, Saadia Gabriel, Lianhui Qin, Dan Jurafsky, Noah A Smith, and Yejin Choi. 2020. [Social bias frames: Reasoning about social and power implications of language](https://md.research.elamur.ai/free/en/papers/sap-2020-social-bias-frames-reasoning-about/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5477–5490.
26. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. [Toolformer: Language models can teach themselves to use tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/). arXiv preprint arXiv:2302.04761.
27. Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Rich James, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2023. [Replug: Retrieval-augmented black-box language models](https://md.research.elamur.ai/free/en/papers/shi-2023-replug-retrieval-augmented-black-box/). arXiv preprint arXiv:2301.12652.
28. Noah Shinn, Beck Labash, and Ashwin Gopinath. 2023. [Reflexion: an autonomous agent with dynamic memory and self-reflection](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/). arXiv preprint arXiv:2303.11366.
29. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. 2019. [CommonsenseQA: A question answering challenge targeting commonsense knowledge](https://md.research.elamur.ai/free/en/papers/talmor-2019-commonsenseqa-question-answering-challenge-targeting/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
30. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford alpaca: An instruction-following llama model. [https://github.com/tatsu-lab/stanford_alpaca](https://github.com/tatsu-lab/stanford_alpaca). [↗](https://github.com/tatsu-lab/stanford_alpaca)
31. Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. 2022. [Lamda: Language models for dialog applications](https://md.research.elamur.ai/free/en/papers/thoppilan-2022-lamda-language-models-dialog-applications/). arXiv preprint arXiv:2201.08239.
32. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971.
33. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, and Denny Zhou. 2022a. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). arXiv preprint arXiv:2203.11171.
34. Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, et al. 2022b. Super-naturalinstructions:generalization via declarative instructions on 1600+ tasks. In EMNLP. [find](https://scholar.google.com/scholar?q=Yizhong+Wang%2C+Swaroop+Mishra%2C+Pegah+Alipoormolabashi%2C+Yeganeh+Kordi%2C+Amirreza+Mirzaei%2C+Anjana+Arunkumar%2C+Arjun+Ashok%2C+Arut+Selvan+Dhanasekaran%2C+Atharva+Naik%2C+David+Stap%2C+et+al%2E+2022b%2E+Super%2Dnaturalins)
35. Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021. [Finetuned language models are zero-shot learners](https://md.research.elamur.ai/free/en/papers/wei-2021-finetuned-language-models-zero-shot/). arXiv preprint arXiv:2109.01652.
36. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. 2022a. [Emergent abilities of large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-emergent-abilities-large-language-models/). arXiv preprint arXiv:2206.07682.
37. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Quoc Le, and Denny Zhou. 2022b. [Chain of thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). arXiv preprint arXiv:2201.11903.
38. Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. [Opt: Open pre-trained transformer language models](https://md.research.elamur.ai/free/en/papers/zhang-2022-opt-open-pre-trained-transformer/). arXiv preprint arXiv:2205.01068.
39. Tianhua Zhang, Hongyin Luo, Yung-Sung Chuang, Wei Fang, Luc Gaitskell, Thomas Hartvigsen, Xixin Wu, Danny Fox, Helen Meng, and James Glass. 2023. [Interpretable unified language checking](https://md.research.elamur.ai/free/en/papers/zhang-2023-interpretable-unified-language-checking/). arXiv preprint arXiv:2304.03728.

*Updated 3 November 2026*