---
title: "Inseq: An Interpretability Toolkit for Sequence Generation Models"
description: "Inseq offers: attribution of the source side, or of the source plus the generated prefix custom… 82 references, cited by 62 papers here."
authors: ["Gabriele Sarti", "Nils Feldhus", "Ludwig Sickert", "Oskar van der Wal", "Malvina Nissim", "Arianna Bisazza"]
year: 2023
venue: "arXiv:2302.13942 · Proceedings of ACL: System Demonstrations (2023) 421-435"
source: "https://arxiv.org/abs/2302.13942"
doi: "10.18653/v1/2023.acl-demo.40"
arxiv: "2302.13942"
licence: "CC BY-SA 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by-sa/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/sarti-2023-inseq-interpretability-toolkit-sequence-generation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sarti-2023-inseq-interpretability-toolkit-sequence-generation/)

[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/6/) / Inseq: An Interpretability Toolkit for Sequence Generation Models

# Inseq: An Interpretability Toolkit for Sequence Generation Models

**Authors:** [Gabriele Sarti](https://md.research.elamur.ai/free/en/authors/gabriele-sarti/), Nils Feldhus, Ludwig Sickert, Oskar van der Wal, [Malvina Nissim](https://md.research.elamur.ai/free/en/authors/malvina-nissim/) and [Arianna Bisazza](https://md.research.elamur.ai/free/en/authors/arianna-bisazza/) · **Year:** 2023 · **Venue:** [arXiv:2302.13942 · Proceedings of ACL: System Demonstrations (2023) 421-435](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2023](https://md.research.elamur.ai/free/en/venues/acl/2023/)) · **Licence:** [CC BY-SA 4.0 (arXiv)](http://creativecommons.org/licenses/by-sa/4.0/)

**Links:** [Publisher's page](https://doi.org/10.18653/v1/2023.acl-demo.40) · [PDF](https://arxiv.org/pdf/2302.13942) · [DOI 10.18653/v1/2023.acl-demo.40](https://doi.org/10.18653/v1/2023.acl-demo.40) · [arXiv 2302.13942](https://arxiv.org/abs/2302.13942) · [OpenAlex](https://openalex.org/W4385570354)

**Citations:** 34 citations (OpenAlex, 2026-10-14) · [62](https://md.research.elamur.ai/free/en/papers/sarti-2023-inseq-interpretability-toolkit-sequence-generation/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Most feature attribution research and tooling in NLP targets classification, where each input token gets a single importance score. Generation is harder. Attribution there spans many steps and yields an input-by-output importance matrix. Previously generated tokens also become inputs, and large vocabularies and decoding strategies complicate things further. Inseq is an open-source Python library (v0.4.0 on PyPI) that fills this gap for decoder-only and encoder-decoder models from the Transformers library. It wraps gradient-based, internals-based and perturbation-based methods, many taken from Captum.

Inseq offers:
- attribution of the source side, or of the source plus the generated prefix
- custom attribution targets and constrained decoding
- chainable aggregation of subword and embedding scores
- batching, a CLI, and saving, reloading and visualizing results

Two case studies show its use: probing gender bias in MT systems, and locating factual knowledge in GPT-2. For the second, the authors propose Contrastive Attribution Tracing (CAT), whose findings agree with costlier causal mediation work. Inseq matters because it standardizes reproducible, comparable interpretability analyses for generative models.

## Key points
- A basic attribution and visualization run takes about three lines of code. The repository is github.com/inseq-team/inseq.
- Supported methods include:
  - Gradient-based: (Input ×) Gradient, DeepLIFT, GradientSHAP, Integrated Gradients and Discretized IG.
  - Internals-based: attention weights.
  - Perturbation-based: Occlusion and LIME.
- Built-in step scores include probability, entropy, cross-entropy, perplexity, contrastive probability difference and MC Dropout probability. Several methods can attribute intermediate layers.
- Using Layer Gradient × Activation, CAT compares a true factual target against a false alternative (e.g. Paris vs. Rome). It was run on 1000 Counterfact statements and needs only one forward and one backward pass.
- Compared with LIT and Ecco, Inseq is positioned for systematic quantitative studies. ERASER, Thermostat, transformers-interpret and ferret lack support for sequence models.

*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

- [University of Amsterdam](https://md.research.elamur.ai/free/en/universities/university-of-amsterdam/) — University, Amsterdam, Netherlands · 89 works · 81,337 citations
- [University of Groningen](https://md.research.elamur.ai/free/en/universities/university-of-groningen/) — University, Groningen, Netherlands · 49 works · 4,843 citations
- [German Research Centre for Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/german-research-centre-for-artificial-intelligence/) — Research institute, Kaiserslautern, Germany · 42 works · 28,596 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 116 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 114 works

🧭 Topics (1): [🔬 Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/) · 58 works

## Cite

Cite as: Gabriele Sarti, Nils Feldhus, Ludwig Sickert, Oskar van der Wal, Malvina Nissim and Arianna Bisazza. 2023. Inseq: An Interpretability Toolkit for Sequence Generation Models. arXiv:2302.13942 · Proceedings of ACL: System Demonstrations (2023) 421-435.

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

```bibtex
@misc{sarti2023inseq,
  title = {{Inseq: An Interpretability Toolkit for Sequence Generation Models}},
  author = {Gabriele Sarti, Nils Feldhus, Ludwig Sickert, Oskar {van der Wal}, Malvina Nissim and Arianna Bisazza},
  year = {2023},
  doi = {10.18653/v1/2023.acl-demo.40},
  eprint = {2302.13942},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2023.acl-demo.40}
}
```

- [← previous FireAct: Toward Language Agent Fine-tuning](https://md.research.elamur.ai/free/en/papers/chen-2023-fireact-toward-language-agent-fine/)
- [next → Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation](https://md.research.elamur.ai/free/en/papers/li-2023-bactrian-x-multilingual-replicable-instruction/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/6/)

## References

82 references, 32 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abubakar Abid, Ali Abdalla, Ali Abid, Dawood Khan, Abdulrahman Alfozan, and James Y. Zou. 2019. Gradio: Hassle-free sharing and testing of ML models in the wild. ArXiv, abs/1906.02569. — [arXiv:1906.02569](https://arxiv.org/abs/1906.02569) [find](https://scholar.google.com/scholar?q=Abubakar+Abid%2C+Ali+Abdalla%2C+Ali+Abid%2C+Dawood+Khan%2C+Abdulrahman+Alfozan%2C+and+James+Y%2E+Zou%2E+2019%2E+Gradio%3A+Hassle%2Dfree+sharing+and+testing+of+ML+models+in+the+wild%2E+ArXiv%2C+abs%2F1906%2E02569%2E+%E2%80%94+%5BarXiv%3A1906%2E0)
2. Samira Abnar and Willem Zuidema. 2020. [Quantifying attention flow in transformers](https://md.research.elamur.ai/free/en/papers/abnar-2020-quantifying-attention-flow-transformers/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4190–4197, Online. Association for Computational Linguistics.
3. Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, and Been Kim. 2018. Sanity checks for saliency maps. In Advances in Neural Information Processing Systems, volume 31, pages 9505–9515, Montréal, Canada. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Julius+Adebayo%2C+Justin+Gilmer%2C+Michael+Muelly%2C+Ian+Goodfellow%2C+Moritz+Hardt%2C+and+Been+Kim%2E+2018%2E+Sanity+checks+for+saliency+maps%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+31%2C+pages)
4. J Alammar. 2021. Ecco: An open source library for the explainability of transformer language models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations, pages 249… [find](https://scholar.google.com/scholar?q=J+Alammar%2E+2021%2E+Ecco%3A+An+open+source+library+for+the+explainability+of+transformer+language+models%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+)
5. David Alvarez-Melis and Tommi Jaakkola. 2017. A causal framework for explaining the predictions of black-box sequence-to-sequence models. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 412–421, Copenhagen, Denmark. Association for Computational Lingu… [find](https://scholar.google.com/scholar?q=David+Alvarez%2DMelis+and+Tommi+Jaakkola%2E+2017%2E+A+causal+framework+for+explaining+the+predictions+of+black%2Dbox+sequence%2Dto%2Dsequence+models%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+)
6. Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, and Isabelle Augenstein. 2020. [A diagnostic study of explainability techniques for text classification](https://md.research.elamur.ai/free/en/papers/atanasova-2020-diagnostic-study-explainability-techniques-text/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3256–3274, Online. Association for Co…
7. Giuseppe Attanasio, Eliana Pastor, Chiara Di Bonaventura, and Debora Nozza. 2022. ferret: a framework for benchmarking explainers on transformers. ArXiv, abs/2208.01575. [find](https://scholar.google.com/scholar?q=Giuseppe+Attanasio%2C+Eliana+Pastor%2C+Chiara+Di+Bonaventura%2C+and+Debora+Nozza%2E+2022%2E+ferret%3A+a+framework+for+benchmarking+explainers+on+transformers%2E+ArXiv%2C+abs%2F2208%2E01575%2E)
8. Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, and Wojciech Samek. 2015. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLOS ONE, 10(7):1–46. [find](https://scholar.google.com/scholar?q=Sebastian+Bach%2C+Alexander+Binder%2C+Gr%C3%A9goire+Montavon%2C+Frederick+Klauschen%2C+Klaus%2DRobert+M%C3%BCller%2C+and+Wojciech+Samek%2E+2015%2E+On+pixel%2Dwise+explanations+for+non%2Dlinear+classifier+decisions+by+layer%2Dwise+re)
9. David Baehrens, Timon Schroeter, Stefan Harmeling, Motoaki Kawanabe, Katja Hansen, and Klaus-Robert Müller. 2010. How to explain individual classification decisions. J. Mach. Learn. Res., 11:1803–1831. [find](https://scholar.google.com/scholar?q=David+Baehrens%2C+Timon+Schroeter%2C+Stefan+Harmeling%2C+Motoaki+Kawanabe%2C+Katja+Hansen%2C+and+Klaus%2DRobert+M%C3%BCller%2E+2010%2E+How+to+explain+individual+classification+decisions%2E+J%2E+Mach%2E+Learn%2E+Res%2E%2C+11%3A1803%E2%80%931831)
10. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. [Neural machine translation by jointly learning to align and translate](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/). In Proceedings of the 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA.
11. Jasmijn Bastings, Sebastian Ebert, Polina Zablotskaia, Anders Sandholm, and Katja Filippova. 2022. “will you find these shortcuts?” a protocol for evaluating the faithfulness of input salience methods for text classification. In Proceedings of the 2022 Conference on Empirical Methods in Natural Lang… [find](https://scholar.google.com/scholar?q=Jasmijn+Bastings%2C+Sebastian+Ebert%2C+Polina+Zablotskaia%2C+Anders+Sandholm%2C+and+Katja+Filippova%2E+2022%2E+%E2%80%9Cwill+you+find+these+shortcuts%3F%E2%80%9D+a+protocol+for+evaluating+the+faithfulness+of+input+salience+methods)
12. Yonatan Belinkov and James Glass. 2019. [Analysis methods in neural language processing: A survey](https://md.research.elamur.ai/free/en/papers/belinkov-2019-analysis-methods-neural-language-processing/). Transactions of the Association for Computational Linguistics, 7:49–72.
13. Su Lin Blodgett, Solon Barocas, Hal Daumé III, and Hanna Wallach. 2020. [Language (technology) is power: A critical survey of “bias” in NLP](https://md.research.elamur.ai/free/en/papers/blodgett-2020-language-technology-is-power-critical/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5454– 5476, Online. Association for Computational Linguistics.
14. Rishi Bommasani and Percy Liang. 2022. Trustworthy social bias measurement. ArXiv, abs/2212.11672. — [arXiv:2212.11672](https://arxiv.org/abs/2212.11672) [find](https://scholar.google.com/scholar?q=Rishi+Bommasani+and+Percy+Liang%2E+2022%2E+Trustworthy+social+bias+measurement%2E+ArXiv%2C+abs%2F2212%2E11672%2E+%E2%80%94+%5BarXiv%3A2212%2E11672%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2212%2E11672%29)
15. Aylin Caliskan, Joanna J. Bryson, and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334):183–186. [find](https://scholar.google.com/scholar?q=Aylin+Caliskan%2C+Joanna+J%2E+Bryson%2C+and+Arvind+Narayanan%2E+2017%2E+Semantics+derived+automatically+from+language+corpora+contain+human%2Dlike+biases%2E+Science%2C+356%286334%29%3A183%E2%80%93186%2E)
16. Won Ik Cho, Ji Won Kim, Seok Min Kim, and Nam Soo Kim. 2019. [On measuring gender bias in translation of gender-neutral pronouns](https://md.research.elamur.ai/free/en/papers/cho-2019-measuring-gender-bias-translation-gender/). In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 173–181, Florence, Italy. Association for Computational Linguistics.
17. George Chrysostomou and Nikolaos Aletras. 2022. An empirical study on explanations in out-of-domain settings. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6920–6938, Dublin, Ireland. Association for Computational Linguistic… [find](https://scholar.google.com/scholar?q=George+Chrysostomou+and+Nikolaos+Aletras%2E+2022%2E+An+empirical+study+on+explanations+in+out%2Dof%2Ddomain+settings%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computational+Linguistics)
18. [Hyung Won Chung, Le Hou, S. Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Dasha Valter, Sharan Narang, Gaurav Mishra, Adams Wei Yu, Vincent Zhao, Ya…](https://md.research.elamur.ai/free/en/papers/chung-2022-scaling-instruction-finetuned-language-models/)
19. Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D. Manning. 2019. What does BERT look at? an analysis of BERT’s attention. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 276–286, Florence, Italy. Association for Computationa… [find](https://scholar.google.com/scholar?q=Kevin+Clark%2C+Urvashi+Khandelwal%2C+Omer+Levy%2C+and+Christopher+D%2E+Manning%2E+2019%2E+What+does+BERT+look+at%3F+an+analysis+of+BERT%E2%80%99s+attention%2E+In+Proceedings+of+the+2019+ACL+Workshop+BlackboxNLP%3A+Analyzing+an)
20. Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, and Furu Wei. 2022. Knowledge neurons in pretrained transformers. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8493– 8502, Dublin, Ireland. Association for Computatio… [find](https://scholar.google.com/scholar?q=Damai+Dai%2C+Li+Dong%2C+Yaru+Hao%2C+Zhifang+Sui%2C+Baobao+Chang%2C+and+Furu+Wei%2E+2022%2E+Knowledge+neurons+in+pretrained+transformers%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computationa)
21. Shi Feng, Eric Wallace, Alvin Grissom II, Mohit Iyyer, Pedro Rodriguez, and Jordan Boyd-Graber. 2018. Pathologies of neural models make interpretations difficult. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3719–3728, Brussels, Belgium. Associatio… [find](https://scholar.google.com/scholar?q=Shi+Feng%2C+Eric+Wallace%2C+Alvin+Grissom+II%2C+Mohit+Iyyer%2C+Pedro+Rodriguez%2C+and+Jordan+Boyd%2DGraber%2E+2018%2E+Pathologies+of+neural+models+make+interpretations+difficult%2E+In+Proceedings+of+the+2018+Conference)
22. David Dale, Elena Voita, Loïc Barrault, and Marta Ruiz Costa-jussà. 2022. [Detecting and mitigating hallucinations in machine translation: Model internal workings alone do well, sentence similarity even better](https://md.research.elamur.ai/free/en/papers/dale-2023-detecting-mitigating-hallucinations-machine-translation/). ArXiv, abs/2212.08597.
23. Javier Ferrando, Gerard I. Gállego, Belen Alastruey, Carlos Escolano, and Marta R. Costa-jussà. 2022. Towards opening the black box of neural machine translation: Source and target interpretations of the transformer. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Proc… [find](https://scholar.google.com/scholar?q=Javier+Ferrando%2C+Gerard+I%2E+G%C3%A1llego%2C+Belen+Alastruey%2C+Carlos+Escolano%2C+and+Marta+R%2E+Costa%2Djuss%C3%A0%2E+2022%2E+Towards+opening+the+black+box+of+neural+machine+translation%3A+Source+and+target+interpretations+of+)
24. Tim Dettmers, Mike Lewis, Younes Belkada, and Luke Zettlemoyer. 2022. GPT3.int8(): 8-bit matrix multiplication for transformers at scale. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Tim+Dettmers%2C+Mike+Lewis%2C+Younes+Belkada%2C+and+Luke+Zettlemoyer%2E+2022%2E+GPT3%2Eint8%28%29%3A+8%2Dbit+matrix+multiplication+for+transformers+at+scale%2E+In+Advances+in+Neural+Information+Processing+Systems%2E)
25. Jay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric Lehman, Caiming Xiong, Richard Socher, and Byron C. Wallace. 2020. [ERASER: A benchmark to evaluate rationalized NLP models](https://md.research.elamur.ai/free/en/papers/deyoung-2020-eraser-benchmark-evaluate-rationalized-nlp/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4443–4458, Online. Asso…
26. Shuoyang Ding, Hainan Xu, and Philipp Koehn. 2019. Saliency-driven word alignment interpretation for neural machine translation. In Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), pages 1–12, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Shuoyang+Ding%2C+Hainan+Xu%2C+and+Philipp+Koehn%2E+2019%2E+Saliency%2Ddriven+word+alignment+interpretation+for+neural+machine+translation%2E+In+Proceedings+of+the+Fourth+Conference+on+Machine+Translation+%28Volume+)
27. Bryan Eikema and Wilker Aziz. 2020. [Is MAP decoding all you need? the inadequacy of the mode in neural machine translation](https://md.research.elamur.ai/free/en/papers/eikema-2020-is-map-decoding-all-you/). In Proceedings of the 28th International Conference on Computational Linguistics, pages 4506–4520, Barcelona, Spain (Online). International Committee on Computational Linguisti…
28. Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, and Armand Joulin. 2021. Beyond english-centric multiling… [find](https://scholar.google.com/scholar?q=Angela+Fan%2C+Shruti+Bhosale%2C+Holger+Schwenk%2C+Zhiyi+Ma%2C+Ahmed+El%2DKishky%2C+Siddharth+Goyal%2C+Mandeep+Baines%2C+Onur+Celebi%2C+Guillaume+Wenzek%2C+Vishrav+Chaudhary%2C+Naman+Goyal%2C+Tom+Birch%2C+Vitaliy+Liptchinsky%2C+S)
29. Anna Farkas and Renáta Németh. 2022. How to measure [gender bias in machine translation](https://md.research.elamur.ai/free/en/papers/savoldi-2021-gender-bias-machine-translation/): Real-world oriented machine translators, multiple reference points. Social Sciences & Humanities Open, 5(1):100239.
30. Nils Feldhus, Robert Schwarzenberg, and Sebastian Möller. 2021. Thermostat: A large collection of NLP model explanations and analysis tools. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 87–95, Online and Punta Cana, Dominican… [find](https://scholar.google.com/scholar?q=Nils+Feldhus%2C+Robert+Schwarzenberg%2C+and+Sebastian+M%C3%B6ller%2E+2021%2E+Thermostat%3A+A+large+collection+of+NLP+model+explanations+and+analysis+tools%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+)
31. Javier Ferrando, Gerard I. G’allego, Ioannis Tsiamas, and Marta Ruiz Costa-jussà. 2023. Explaining how transformers use context to build predictions. ArXiv, abs/2305.12535. [find](https://scholar.google.com/scholar?q=Javier+Ferrando%2C+Gerard+I%2E+G%E2%80%99allego%2C+Ioannis+Tsiamas%2C+and+Marta+Ruiz+Costa%2Djuss%C3%A0%2E+2023%2E+Explaining+how+transformers+use+context+to+build+predictions%2E+ArXiv%2C+abs%2F2305%2E12535%2E)
32. Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of The 33rd International Conference on Machine Learning, volume 48 of Proceedings of Machine Learning Research, pages 1050–1059, New York, NY, USA. Proceedings… [find](https://scholar.google.com/scholar?q=Yarin+Gal+and+Zoubin+Ghahramani%2E+2016%2E+Dropout+as+a+bayesian+approximation%3A+Representing+model+uncertainty+in+deep+learning%2E+In+Proceedings+of+The+33rd+International+Conference+on+Machine+Learning%2C+vo)
33. Shilin He, Zhaopeng Tu, Xing Wang, Longyue Wang, Michael Lyu, and Shuming Shi. 2019. Towards understanding neural machine translation with word importance. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural… [find](https://scholar.google.com/scholar?q=Shilin+He%2C+Zhaopeng+Tu%2C+Xing+Wang%2C+Longyue+Wang%2C+Michael+Lyu%2C+and+Shuming+Shi%2E+2019%2E+Towards+understanding+neural+machine+translation+with+word+importance%2E+In+Proceedings+of+the+2019+Conference+on+Emp)
34. Alon Jacovi and Yoav Goldberg. 2020. [Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness?](https://md.research.elamur.ai/free/en/papers/jacovi-2020-faithfully-interpretable-nlp-systems-how/) In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4198–4205, Online. Association for Computational Linguistics.
35. Sarthak Jain, Varun Manjunatha, Byron Wallace, and Ani Nenkova. 2022. Influence functions for sequence tagging models. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 824–839, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sarthak+Jain%2C+Varun+Manjunatha%2C+Byron+Wallace%2C+and+Ani+Nenkova%2E+2022%2E+Influence+functions+for+sequence+tagging+models%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2022%2C+pages+8)
36. Sarthak Jain and Byron C. Wallace. 2019. [Attention is not Explanation](https://md.research.elamur.ai/free/en/papers/jain-2019-attention-is-not-explanation/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3543–3556, Minneapolis, Minnesota. Associa…
37. Zhiying Jiang, Raphael Tang, Ji Xin, and Jimmy Lin. 2020. Inserting Information Bottlenecks for Attribution in Transformers. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3850–3857, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Zhiying+Jiang%2C+Raphael+Tang%2C+Ji+Xin%2C+and+Jimmy+Lin%2E+2020%2E+Inserting+Information+Bottlenecks+for+Attribution+in+Transformers%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2020%2C+p)
38. Andrei Kapishnikov, Subhashini Venugopalan, Besim Avci, Ben Wedin, Michael Terry, and Tolga Bolukbasi. 2021. Guided integrated gradients: An adaptive path method for removing noise. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5050–5058. [find](https://scholar.google.com/scholar?q=Andrei+Kapishnikov%2C+Subhashini+Venugopalan%2C+Besim+Avci%2C+Ben+Wedin%2C+Michael+Terry%2C+and+Tolga+Bolukbasi%2E+2021%2E+Guided+integrated+gradients%3A+An+adaptive+path+method+for+removing+noise%2E+In+Proceedings+of+)
39. Jared Kaplan, Sam McCandlish, T. J. Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeff Wu, and Dario Amodei. 2020. [Scaling laws for neural language models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/). ArXiv, abs/2001.08361.
40. Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, and Kentaro Inui. 2020. [Attention is not only a weight: Analyzing transformers with vector norms](https://md.research.elamur.ai/free/en/papers/kobayashi-2020-attention-is-not-only-weight/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7057–7075, Online. Association for Computational…
41. Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, and Kentaro Inui. 2021. Incorporating Residual and Normalization Layers into Analysis of Masked Language Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4547–4568, Online and Punta Cana, Dominica… [find](https://scholar.google.com/scholar?q=Goro+Kobayashi%2C+Tatsuki+Kuribayashi%2C+Sho+Yokoi%2C+and+Kentaro+Inui%2E+2021%2E+Incorporating+Residual+and+Normalization+Layers+into+Analysis+of+Masked+Language+Models%2E+In+Proceedings+of+the+2021+Conference+o)
42. Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, and Kentaro Inui. 2023. Feed-forward blocks control contextualization in masked language models. ArXiv, abs/2302.00456. — [arXiv:2302.00456](https://arxiv.org/abs/2302.00456) [find](https://scholar.google.com/scholar?q=Goro+Kobayashi%2C+Tatsuki+Kuribayashi%2C+Sho+Yokoi%2C+and+Kentaro+Inui%2E+2023%2E+Feed%2Dforward+blocks+control+contextualization+in+masked+language+models%2E+ArXiv%2C+abs%2F2302%2E00456%2E+%E2%80%94+%5BarXiv%3A2302%2E00456%5D%28https%3A%2F%2Farx)
43. Narine Kokhlikyan, Vivek Miglani, Miguel Martin, Edward Wang, Bilal Alsallakh, Jonathan Reynolds, Alexander Melnikov, Natalia Kliushkina, Carlos Araya, Siqi Yan, and Orion Reblitz-Richardson. 2020. Captum: A unified and generic model interpretability library for pytorch. ArXiv, abs/2009.07896. — [arXiv:2009.07896](https://arxiv.org/abs/2009.07896) [find](https://scholar.google.com/scholar?q=Narine+Kokhlikyan%2C+Vivek+Miglani%2C+Miguel+Martin%2C+Edward+Wang%2C+Bilal+Alsallakh%2C+Jonathan+Reynolds%2C+Alexander+Melnikov%2C+Natalia+Kliushkina%2C+Carlos+Araya%2C+Siqi+Yan%2C+and+Orion+Reblitz%2DRichardson%2E+2020%2E+Ca)
44. Tsz Kin Lam, Eva Hasler, and Felix Hieber. 2022. Analyzing the use of influence functions for instance-specific data filtering in neural machine translation. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 295–309, Abu Dhabi, United Arab Emirates (Hybrid). Association fo… [find](https://scholar.google.com/scholar?q=Tsz+Kin+Lam%2C+Eva+Hasler%2C+and+Felix+Hieber%2E+2022%2E+Analyzing+the+use+of+influence+functions+for+instance%2Dspecific+data+filtering+in+neural+machine+translation%2E+In+Proceedings+of+the+Seventh+Conference+o)
45. Shahar Levy, Koren Lazar, and Gabriel Stanovsky. 2021. [Collecting a large-scale gender bias dataset for coreference resolution and machine translation](https://md.research.elamur.ai/free/en/papers/levy-2021-collecting-large-scale-gender-bias/). In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2470–2480, Punta Cana, Dominican Republic. Association for Computati…
46. [Quentin Lhoest, Albert Villanova del Moral, Yacine Jernite, Abhishek Thakur, Patrick von Platen, Suraj Patil, Julien Chaumond, Mariama Drame, Julien Plu, Lewis Tunstall, Joe Davison, Mario Šaško, Gunjan Chhablani, Bhavitvya Malik, Simon Brandeis, Teven Le Scao, Victor Sanh, Canwen Xu, Nicolas Patry,…](https://md.research.elamur.ai/free/en/papers/lhoest-2021-datasets-community-library-natural-language/)
47. Scott M. Lundberg and Su-In Lee. 2017. [A unified approach to interpreting model predictions](https://md.research.elamur.ai/free/en/papers/lundberg-2017-unified-approach-interpreting-model-predictions/). In Proceedings of the 31st International Conference on Neural Information Processing Systems, volume 30, page 4768–4777, Long Beach, California, USA. Curran Associates Inc.
48. Andreas Madsen, Nicholas Meade, Vaibhav Adlakha, and Siva Reddy. 2022a. Evaluating the faithfulness of importance measures in NLP by recursively masking allegedly important tokens and retraining. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1731–1751, Abu Dhabi, Un… [find](https://scholar.google.com/scholar?q=Andreas+Madsen%2C+Nicholas+Meade%2C+Vaibhav+Adlakha%2C+and+Siva+Reddy%2E+2022a%2E+Evaluating+the+faithfulness+of+importance+measures+in+NLP+by+recursively+masking+allegedly+important+tokens+and+retraining%2E+In+F)
49. Andreas Madsen, Siva Reddy, and Sarath Chandar. 2022b. Post-hoc interpretability for neural nlp: A survey. ACM Comput. Surv., 55(8). [find](https://scholar.google.com/scholar?q=Andreas+Madsen%2C+Siva+Reddy%2C+and+Sarath+Chandar%2E+2022b%2E+Post%2Dhoc+interpretability+for+neural+nlp%3A+A+survey%2E+ACM+Comput%2E+Surv%2E%2C+55%288%29%2E)
50. Kevin Meng, David Bau, Alex J Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in GPT. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Kevin+Meng%2C+David+Bau%2C+Alex+J+Andonian%2C+and+Yonatan+Belinkov%2E+2022%2E+Locating+and+editing+factual+associations+in+GPT%2E+In+Advances+in+Neural+Information+Processing+Systems%2E)
51. Ali Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh, and Mohammad Taher Pilehvar. 2022. GlobEnc: Quantifying global token attribution by incorporating the whole encoder layer in transformers. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Li… [find](https://scholar.google.com/scholar?q=Ali+Modarressi%2C+Mohsen+Fayyaz%2C+Yadollah+Yaghoobzadeh%2C+and+Mohammad+Taher+Pilehvar%2E+2022%2E+GlobEnc%3A+Quantifying+global+token+attribution+by+incorporating+the+whole+encoder+layer+in+transformers%2E+In+Proc)
52. Hosein Mohebbi, Willem H. Zuidema, Grzegorz Chrupała, and A. Alishahi. 2023. Quantifying context mixing in transformers. ArXiv, abs/2301.12971. [find](https://scholar.google.com/scholar?q=Hosein+Mohebbi%2C+Willem+H%2E+Zuidema%2C+Grzegorz+Chrupa%C5%82a%2C+and+A%2E+Alishahi%2E+2023%2E+Quantifying+context+mixing+in+transformers%2E+ArXiv%2C+abs%2F2301%2E12971%2E)
53. Neel Nanda. 2023. Attribution patching: Activation patching at industrial scale. Blog post. [find](https://scholar.google.com/scholar?q=Neel+Nanda%2E+2023%2E+Attribution+patching%3A+Activation+patching+at+industrial+scale%2E+Blog+post%2E)
54. Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, and Michael Auli. 2019. [fairseq: A fast, extensible toolkit for sequence modeling](https://md.research.elamur.ai/free/en/papers/ott-2019-fairseq-fast-extensible-toolkit-sequence/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstr…
55. Charles Pierse. 2021. Transformers interpret. Python library. [find](https://scholar.google.com/scholar?q=Charles+Pierse%2E+2021%2E+Transformers+interpret%2E+Python+library%2E)
56. Marcelo OR Prates, Pedro H Avelar, and Luís C Lamb. 2020. Assessing [gender bias in machine translation](https://md.research.elamur.ai/free/en/papers/savoldi-2021-gender-bias-machine-translation/): a case study with google translate. Neural Computing and Applications, 32:6363–6381.
57. Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeff+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+Blog%2E)
58. Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 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, KDD ’16, page 1135–1144, New York, NY, USA. Association for Co…
59. Rachel Rudinger, Jason Naradowsky, Brian Leonard, and Benjamin Van Durme. 2018. [Gender bias in coreference resolution](https://md.research.elamur.ai/free/en/papers/rudinger-2018-gender-bias-coreference-resolution/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 8–1…
60. Soumya Sanyal and Xiang Ren. 2021. Discretized integrated gradients for explaining language models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10285–10299, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Soumya+Sanyal+and+Xiang+Ren%2E+2021%2E+Discretized+integrated+gradients+for+explaining+language+models%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+102)
61. Beatrice Savoldi, Marco Gaido, Luisa Bentivogli, Matteo Negri, and Marco Turchi. 2021. [Gender bias in machine translation](https://md.research.elamur.ai/free/en/papers/savoldi-2021-gender-bias-machine-translation/). Transactions of the Association for Computational Linguistics, 9:845–874.
62. Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. 2017. [Learning important features through propagating activation differences](https://md.research.elamur.ai/free/en/papers/shrikumar-2017-learning-important-features-through-propagating/). In Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 3145–3153. PMLR.
63. Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2013. [Deep inside convolutional networks: Visualising image classification models and saliency maps](https://md.research.elamur.ai/free/en/papers/simonyan-2013-deep-inside-convolutional-networks-visualising/). arXiv.
64. Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In Proceedings of the 34th International Conference on Machine Learning (ICML), volume 70, page 3319–3328. Journal of Machine Learning Research (JMLR). [find](https://scholar.google.com/scholar?q=Mukund+Sundararajan%2C+Ankur+Taly%2C+and+Qiqi+Yan%2E+2017%2E+Axiomatic+attribution+for+deep+networks%2E+In+Proceedings+of+the+34th+International+Conference+on+Machine+Learning+%28ICML%29%2C+volume+70%2C+page+3319%E2%80%933328%2E)
65. Zeerak Talat, Aurélie Névéol, Stella Biderman, Miruna Clinciu, Manan Dey, Shayne Longpre, Sasha Luccioni, Maraim Masoud, Margaret Mitchell, Dragomir Radev, Shanya Sharma, Arjun Subramonian, Jaesung Tae, Samson Tan, Deepak Tunuguntla, and Oskar Van Der Wal. 2022. [You reap what you sow: On the challen…](https://md.research.elamur.ai/free/en/papers/talat-2022-you-reap-what-you-sow/)
66. Joel Tang, M. Fomicheva, and Lucia Specia. 2022. Reducing hallucinations in neural machine translation with feature attribution. ArXiv, abs/2211.09878. — [arXiv:2211.09878](https://arxiv.org/abs/2211.09878) [find](https://scholar.google.com/scholar?q=Joel+Tang%2C+M%2E+Fomicheva%2C+and+Lucia+Specia%2E+2022%2E+Reducing+hallucinations+in+neural+machine+translation+with+feature+attribution%2E+ArXiv%2C+abs%2F2211%2E09878%2E+%E2%80%94+%5BarXiv%3A2211%2E09878%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2211%2E)
67. Ian Tenney, James Wexler, Jasmijn Bastings, Tolga Bolukbasi, Andy Coenen, Sebastian Gehrmann, Ellen Jiang, Mahima Pushkarna, Carey Radebaugh, Emily Reif, and Ann Yuan. 2020. The language interpretability tool: Extensible, interactive visualizations and analysis for NLP models. In Proceedings of the… [find](https://scholar.google.com/scholar?q=Ian+Tenney%2C+James+Wexler%2C+Jasmijn+Bastings%2C+Tolga+Bolukbasi%2C+Andy+Coenen%2C+Sebastian+Gehrmann%2C+Ellen+Jiang%2C+Mahima+Pushkarna%2C+Carey+Radebaugh%2C+Emily+Reif%2C+and+Ann+Yuan%2E+2020%2E+The+language+interpretabil)
68. Jörg Tiedemann. 2020. [The tatoeba translation challenge – realistic data sets for low resource and multilingual MT](https://md.research.elamur.ai/free/en/papers/tiedemann-2020-tatoeba-translation-challenge-realistic-data/). In Proceedings of the Fifth Conference on Machine Translation, pages 1174–1182, Online. Association for Computational Linguistics.
69. Keyon Vafa, Yuntian Deng, David Blei, and Alexander Rush. 2021. Rationales for sequential predictions. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10314–10332, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Keyon+Vafa%2C+Yuntian+Deng%2C+David+Blei%2C+and+Alexander+Rush%2E+2021%2E+Rationales+for+sequential+predictions%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+)
70. Jannis Vamvas and Rico Sennrich. 2021. On the limits of minimal pairs in contrastive evaluation. In Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 58–68, Punta Cana, Dominican Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jannis+Vamvas+and+Rico+Sennrich%2E+2021%2E+On+the+limits+of+minimal+pairs+in+contrastive+evaluation%2E+In+Proceedings+of+the+Fourth+BlackboxNLP+Workshop+on+Analyzing+and+Interpreting+Neural+Networks+for+NLP)
71. Oskar van der Wal, Dominik Bachmann, Alina Leidinger, Leendert van Maanen, Willem Zuidema, and Katrin Schulz. 2022. Undesirable biases in nlp: Averting a crisis of measurement. ArXiv, abs/2211.13709. — [arXiv:2211.13709](https://arxiv.org/abs/2211.13709) [find](https://scholar.google.com/scholar?q=Oskar+van+der+Wal%2C+Dominik+Bachmann%2C+Alina+Leidinger%2C+Leendert+van+Maanen%2C+Willem+Zuidema%2C+and+Katrin+Schulz%2E+2022%2E+Undesirable+biases+in+nlp%3A+Averting+a+crisis+of+measurement%2E+ArXiv%2C+abs%2F2211%2E13709%2E+)
72. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 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. Curran Associates, Inc.
73. Elena Voita, Rico Sennrich, and Ivan Titov. 2021a. Analyzing the source and target contributions to predictions in neural machine translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Pr… [find](https://scholar.google.com/scholar?q=Elena+Voita%2C+Rico+Sennrich%2C+and+Ivan+Titov%2E+2021a%2E+Analyzing+the+source+and+target+contributions+to+predictions+in+neural+machine+translation%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Associat)
74. Elena Voita, Rico Sennrich, and Ivan Titov. 2021b. Language modeling, lexical translation, reordering: The training process of NMT through the lens of classical SMT. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8478–8491, Online and Punta Cana, Dom… [find](https://scholar.google.com/scholar?q=Elena+Voita%2C+Rico+Sennrich%2C+and+Ivan+Titov%2E+2021b%2E+Language+modeling%2C+lexical+translation%2C+reordering%3A+The+training+process+of+NMT+through+the+lens+of+classical+SMT%2E+In+Proceedings+of+the+2021+Confere)
75. Elena Voita, Pavel Serdyukov, Rico Sennrich, and Ivan Titov. 2018. [Context-aware neural machine translation learns anaphora resolution](https://md.research.elamur.ai/free/en/papers/voita-2018-context-aware-neural-machine-translation/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1264–1274, Melbourne, Australia. Associati…
76. Eric Wallace, Matt Gardner, and Sameer Singh. 2020. Interpreting predictions of NLP models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, pages 20–23, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Eric+Wallace%2C+Matt+Gardner%2C+and+Sameer+Singh%2E+2020%2E+Interpreting+predictions+of+NLP+models%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Language+Processing%3A+Tutorial+Abstract)
77. [Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lho…](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/)
78. Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. [Show, attend and tell: Neural image caption generation with visual attention](https://md.research.elamur.ai/free/en/papers/xu-2015-show-attend-tell-neural-image/). In Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings o…
79. Weijia Xu, Sweta Agrawal, Eleftheria Briakou, Marianna J. Martindale, and Marine Carpuat. 2023. Understanding and detecting hallucinations in neural machine translation via model introspection. ArXiv, abs/2301.07779. [find](https://scholar.google.com/scholar?q=Weijia+Xu%2C+Sweta+Agrawal%2C+Eleftheria+Briakou%2C+Marianna+J%2E+Martindale%2C+and+Marine+Carpuat%2E+2023%2E+Understanding+and+detecting+hallucinations+in+neural+machine+translation+via+model+introspection%2E+ArXiv%2C)
80. Kayo Yin and Graham Neubig. 2022. Interpreting language models with contrastive explanations. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 184–198, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Kayo+Yin+and+Graham+Neubig%2E+2022%2E+Interpreting+language+models+with+contrastive+explanations%2E+In+Proceedings+of+the+2022+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+184%E2%80%93198%2C+)
81. Muhammad Bilal Zafar, Michele Donini, Dylan Slack, Cedric Archambeau, Sanjiv Das, and Krishnaram Kenthapadi. 2021. On the lack of robust interpretability of neural text classifiers. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3730–3740, Online. Association fo… [find](https://scholar.google.com/scholar?q=Muhammad+Bilal+Zafar%2C+Michele+Donini%2C+Dylan+Slack%2C+Cedric+Archambeau%2C+Sanjiv+Das%2C+and+Krishnaram+Kenthapadi%2E+2021%2E+On+the+lack+of+robust+interpretability+of+neural+text+classifiers%2E+In+Findings+of+the)
82. Matthew D. Zeiler and Rob Fergus. 2014. [Visualizing and understanding convolutional networks](https://md.research.elamur.ai/free/en/papers/zeiler-2013-visualizing-understanding-convolutional-networks/). In Computer Vision – ECCV 2014, pages 818–833, Cham. Springer International Publishing.

*Updated 24 October 2026*