--- title: "Interpretability — papers" description: "Interpretability: 47 papers of the Elamur Research library, the most cited first." canonical: "https://research.elamur.ai/free/en/topics/interpretability/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/topics/interpretability/) [home](https://md.research.elamur.ai/free/en/) / [topics](https://md.research.elamur.ai/free/en/topics/) / Interpretability # 🔬 Interpretability 47 papers · page 1 of 2 · the most cited first · [all topics](https://md.research.elamur.ai/free/en/topics/) What neural models have learned inside, and how to show why they decide as they do. 💡 Explained: [Transformer and attention](https://md.research.elamur.ai/free/en/concepts/transformer/) **1** [2](https://md.research.elamur.ai/free/en/topics/interpretability/page/2/) [next →](https://md.research.elamur.ai/free/en/topics/interpretability/page/2/) - [Towards A Rigorous Science of Interpretable Machine Learning](https://md.research.elamur.ai/free/en/papers/doshi-2017-velez-towards-rigorous-science-interpretable-machine/) — Finale Doshi-Velez, Been Kim · 2017 · 3 202 citations - [What Does BERT Learn about the Structure of Language?](https://md.research.elamur.ai/free/en/papers/jawahar-2019-what-does-bert-learn-about/) — Ganesh Jawahar, Benoît Sagot, Djamé Seddah · 2019 · 1 789 citations - [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/) — Karen Simonyan, Andrea Vedaldi, Andrew Zisserman · 2013 · 1 153 citations - [What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties](https://md.research.elamur.ai/free/en/papers/conneau-2018-what-you-can-cram-into/) — Alexis Conneau, German Kruszewski, Guillaume Lample, et al. · 2018 · 1 021 citations - [Explainability for Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/zhao-2023-explainability-large-language-models-survey/) — Haiyan Zhao, Hanjie Chen, Fan Yang, et al. · 2023 · 785 citations - [SemEval-2015 Task 2: Semantic Textual Similarity, English, Spanish and Pilot on Interpretability](https://md.research.elamur.ai/free/en/papers/agirre-2015-semeval-2015-task-2-semantic/) — Eneko Agirre, Carmen Banea, Claire Cardie, et al. · 2015 · 758 citations - [What do you learn from context? Probing for sentence structure in contextualized word representations](https://md.research.elamur.ai/free/en/papers/tenney-2019-learn-context-probing-sentence-structure/) — Ian Tenney, Patrick Xia, Berlin Chen, et al. · 2019 · 582 citations - [Probing Classifiers: Promises, Shortcomings, and Advances](https://md.research.elamur.ai/free/en/papers/belinkov-2022-probing-classifiers-promises-shortcomings-advances/) — Yonatan Belinkov · 2022 · 513 citations - [Factual Probing Is MASK: Learning vs. Learning to Recall](https://md.research.elamur.ai/free/en/papers/zhong-2021-factual-probing-is-mask-learning/) — Zexuan Zhong, Dan Friedman, Danqi Chen · 2021 · 411 citations - [Do NLP Models Know Numbers? Probing Numeracy in Embeddings](https://md.research.elamur.ai/free/en/papers/wallace-2019-do-nlp-models-know-numbers/) — Eric Wallace, Yizhong Wang, Sujian Li, et al. · 2019 · 348 citations - [Information-Theoretic Probing with Minimum Description Length](https://md.research.elamur.ai/free/en/papers/voita-2020-information-theoretic-probing-minimum-description/) — Elena Voita, Ivan Titov · 2020 · 339 citations - [Probing Pretrained Language Models for Lexical Semantics](https://md.research.elamur.ai/free/en/papers/vulic-2020-probing-pretrained-language-models-lexical/) — Ivan Vulić, Edoardo Maria Ponti, Robert Litschko, et al. · 2020 · 320 citations - [Information-Theoretic Probing for Linguistic Structure](https://md.research.elamur.ai/free/en/papers/pimentel-2020-information-theoretic-probing-linguistic-structure/) — Tiago Pimentel, Josef Valvoda, Rowan Hall Maudslay, et al. · 2020 · 293 citations - [A Survey of the State of Explainable AI for Natural Language Processing](https://md.research.elamur.ai/free/en/papers/danilevsky-2020-survey-state-explainable-ai-natural/) — Marina Danilevsky, Kun Qian, Ranit Aharonov, et al. · 2020 · 290 citations - [A Diagnostic Study of Explainability Techniques for Text Classification](https://md.research.elamur.ai/free/en/papers/atanasova-2020-diagnostic-study-explainability-techniques-text/) — Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, et al. · 2020 · 273 citations - [Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT](https://md.research.elamur.ai/free/en/papers/wu-2020-perturbed-masking-parameter-free-probing/) — Zhiyong Wu, Yun Chen, Ben Kao, et al. · 2020 · 244 citations - [Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals](https://md.research.elamur.ai/free/en/papers/elazar-2021-amnesic-probing-behavioral-explanation-amnesic/) — Yanai Elazar, Shauli Ravfogel, Alon Jacovi, et al. · 2021 · 241 citations - [Probing for semantic evidence of composition by means of simple classification tasks](https://md.research.elamur.ai/free/en/papers/ettinger-2016-probing-semantic-evidence-composition-means/) — Allyson Ettinger, Ahmed Elgohary, Philip Resnik · 2016 · 217 citations - [Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-Trained Language Models](https://md.research.elamur.ai/free/en/papers/lin-2020-birds-have-four-legs-numersense/) — Bill Yuchen Lin, Seyeon Lee, Rahul Khanna, et al. · 2020 · 216 citations - [Probing the Need for Visual Context in Multimodal Machine Translation](https://md.research.elamur.ai/free/en/papers/caglayan-2019-probing-need-visual-context-multimodal/) — Ozan Caglayan, Pranava Madhyastha, Lucia Specia, et al. · 2019 · 214 citations - [Progress measures for grokking via mechanistic interpretability](https://md.research.elamur.ai/free/en/papers/nanda-2023-progress-measures-grokking-mechanistic-interpretability/) — Neel Nanda, Lawrence Chan, Tom Lieberum, et al. · 2023 · 207 citations - [Probing What Different NLP Tasks Teach Machines about Function Word Comprehension](https://md.research.elamur.ai/free/en/papers/kim-2019-probing-what-different-nlp-tasks/) — Najoung Kim, Roma Patel, Adam Poliak, et al. · 2019 · 161 citations - [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://md.research.elamur.ai/free/en/papers/arora-2023-probing-pre-trained-language-models/) — Arnav Arora, Lucie-aimée Kaffee, Isabelle Augenstein · 2023 · 155 citations - [Probing Natural Language Inference Models through Semantic Fragments](https://md.research.elamur.ai/free/en/papers/richardson-2019-probing-natural-language-inference-models/) — Kyle Richardson, Hai Hu, Lawrence S. Moss, et al. · 2019 · 102 citations - [Probing for idiomaticity in vector space models](https://md.research.elamur.ai/free/en/papers/garcia-2021-probing-idiomaticity-vector-space-models/) — Marcos Garcia, Tiago Kramer Vieira, Carolina Scarton, et al. · 2021 · 89 citations **1** [2](https://md.research.elamur.ai/free/en/topics/interpretability/page/2/) [next →](https://md.research.elamur.ai/free/en/topics/interpretability/page/2/) - [← previous topic Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) - [next topic → Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) - [↑ back to topics](https://md.research.elamur.ai/free/en/topics/)