{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"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":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291},{"id":"2006.12013","title":"CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information","created":"2020-06-22","cited_by_count":235},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"2004.03061","title":"Information-Theoretic Probing for Linguistic Structure","created":"2020-04-07","cited_by_count":207},{"id":"1811.04251","title":"Formal Limitations on the Measurement of Mutual Information","created":"2018-11-10","cited_by_count":189},{"id":"2002.10689","title":"A Theory of Usable Information Under Computational Constraints","created":"2020-02-25","cited_by_count":162},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"1910.06222","title":"Understanding the Limitations of Variational Mutual Information Estimators","created":"2019-10-14","cited_by_count":140},{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125},{"id":"2010.04119","title":"Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?","created":"2020-10-08","cited_by_count":95},{"id":"2012.00893","title":"Evaluating Explanations: How much do explanations from the teacher aid students?","created":"2020-12-01","cited_by_count":94},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92},{"id":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78},{"id":"2206.01254","title":"Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations","created":"2022-06-02","cited_by_count":77},{"id":"2109.11635","title":"Revisiting the Uniform Information Density Hypothesis","created":"2021-09-23","cited_by_count":68},{"id":"2109.09234","title":"Conditional probing: measuring usable information beyond a baseline","created":"2021-09-19","cited_by_count":62},{"id":"2106.12543","title":"Synthetic Benchmarks for Scientific Research in Explainable Machine Learning","created":"2021-06-23","cited_by_count":59},{"id":"2306.11078","title":"Beyond Normal: On the Evaluation of Mutual Information Estimators","created":"2023-06-19","cited_by_count":37},{"id":"2010.04736","title":"Evaluating and Characterizing Human Rationales","created":"2020-10-09","cited_by_count":36},{"id":"2109.03853","title":"A Bayesian Framework for Information-Theoretic Probing","created":"2021-09-08","cited_by_count":22},{"id":"2210.04982","title":"REV: Information-Theoretic Evaluation of Free-Text Rationales","created":"2022-10-10","cited_by_count":22},{"id":"2202.06618","title":"A Differential Entropy Estimator for Training Neural Networks","created":"2022-02-14","cited_by_count":20},{"id":"2203.17213","title":"Analyzing Wrap-Up Effects through an Information-Theoretic Lens","created":"2022-03-31","cited_by_count":10},{"id":"2105.02629","title":"Bird's Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach","created":"2021-05-06","cited_by_count":9},{"id":"2003.00484","title":"An Information-Theoretic Approach to Personalized Explainable Machine Learning","created":"2020-03-01","cited_by_count":3},{"id":"2110.08931","title":"Quantifying the Task-Specific Information in Text-Based Classifications","created":"2021-10-17","cited_by_count":3}],"next_cursor":null}