{"list":"other","total":193,"rows":[{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"2004.07667","title":"Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection","created":"2020-04-16","cited_by_count":455},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412},{"id":"1812.05271","title":"TextBugger: Generating Adversarial Text Against Real-world Applications","created":"2018-12-13","cited_by_count":381},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"1606.08813","title":"European Union regulations on algorithmic decision-making and a \"right to explanation\"","created":"2016-06-28","cited_by_count":344},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"1711.02173","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","created":"2017-11-06","cited_by_count":306},{"id":"1901.04592","title":"Interpretable machine learning: definitions, methods, and applications","created":"2019-01-14","cited_by_count":305},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1812.08951","title":"Analysis Methods in Neural Language Processing: A Survey","created":"2018-12-21","cited_by_count":277},{"id":"1802.07810","title":"Manipulating and Measuring Model Interpretability","created":"2018-02-21","cited_by_count":256},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243},{"id":"1910.07969","title":"On Completeness-aware Concept-Based Explanations in Deep Neural Networks","created":"2019-10-17","cited_by_count":239},{"id":"2104.13733","title":"Gradient-based Adversarial Attacks against Text Transformers","created":"2021-04-15","cited_by_count":234},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"1608.04207","title":"Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks","created":"2016-08-15","cited_by_count":216},{"id":"1803.11138","title":"Colorless green recurrent networks dream hierarchically","created":"2018-03-29","cited_by_count":213},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209},{"id":"1803.04765","title":"Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning","created":"2018-03-13","cited_by_count":207},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207},{"id":"2010.00711","title":"A Survey of the State of Explainable AI for Natural Language Processing","created":"2020-10-01","cited_by_count":206},{"id":"2402.16822","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","created":"2024-02-26","cited_by_count":205},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178},{"id":"1408.3456","title":"SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation","created":"2014-08-15","cited_by_count":172},{"id":"1905.08883","title":"Explainable Machine Learning for Scientific Insights and Discoveries","created":"2019-05-21","cited_by_count":166},{"id":"2403.07183","title":"Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews","created":"2024-03-11","cited_by_count":164},{"id":"2004.02105","title":"Unsupervised Domain Clusters in Pretrained Language Models","created":"2020-04-05","cited_by_count":160},{"id":"1811.07901","title":"On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection","created":"2018-11-19","cited_by_count":159},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"2005.00719","title":"Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?","created":"2020-05-02","cited_by_count":151},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"2001.08298","title":"Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems","created":"2020-01-22","cited_by_count":139},{"id":"2106.06087","title":"Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models","created":"2021-06-10","cited_by_count":131},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130},{"id":"2108.12084","title":"Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies","created":"2021-08-27","cited_by_count":128},{"id":"1905.08160","title":"Interpretable Neural Predictions with Differentiable Binary Variables","created":"2019-05-20","cited_by_count":126},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"2311.04897","title":"Future Lens: Anticipating Subsequent Tokens from a Single Hidden State","created":"2023-11-08","cited_by_count":121},{"id":"2005.13407","title":"CausaLM: Causal Model Explanation Through Counterfactual Language Models","created":"2020-05-27","cited_by_count":117},{"id":"2005.00115","title":"Learning to Faithfully Rationalize by Construction","created":"2020-04-30","cited_by_count":113},{"id":"1811.01157","title":"Identifying and Controlling Important Neurons in Neural Machine Translation","created":"2018-11-03","cited_by_count":111},{"id":"2403.00745","title":"AtP*: An efficient and scalable method for localizing LLM behaviour to components","created":"2024-03-01","cited_by_count":111},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110},{"id":"2004.14786","title":"Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT","created":"2020-04-30","cited_by_count":109},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108},{"id":"2012.13985","title":"Explaining NLP Models via Minimal Contrastive Editing (MiCE)","created":"2020-12-27","cited_by_count":106},{"id":"2401.06730","title":"Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty","created":"2024-01-12","cited_by_count":106},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101},{"id":"2402.04049","title":"Systematic Biases in LLM Simulations of Debates","created":"2024-02-06","cited_by_count":99},{"id":"2002.09815","title":"Neuron Shapley: Discovering the Responsible Neurons","created":"2020-02-23","cited_by_count":98},{"id":"2010.02066","title":"Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks","created":"2020-10-05","cited_by_count":98},{"id":"1808.08079","title":"Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information","created":"2018-08-24","cited_by_count":97},{"id":"2010.02695","title":"Analyzing Individual Neurons in Pre-trained Language Models","created":"2020-10-06","cited_by_count":97},{"id":"2005.12116","title":"NILE : Natural Language Inference with Faithful Natural Language Explanations","created":"2020-05-25","cited_by_count":96},{"id":"2004.12406","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","created":"2020-04-26","cited_by_count":93},{"id":"1809.00042","title":"What do RNN Language Models Learn about Filler-Gap Dependencies?","created":"2018-08-31","cited_by_count":86}],"next_cursor":"100"}