{"list":"other","total":60,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"1604.03540","title":"Training Region-based Object Detectors with Online Hard Example Mining","created":"2016-04-12","cited_by_count":579},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2006.09462","title":"Selective Question Answering under Domain Shift","created":"2020-06-16","cited_by_count":238},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"1910.09753","title":"MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension","created":"2019-10-22","cited_by_count":184},{"id":"1906.05416","title":"Synthetic QA Corpora Generation with Roundtrip Consistency","created":"2019-06-12","cited_by_count":143},{"id":"1404.1100","title":"A Tutorial on Principal Component Analysis","created":"2014-04-03","cited_by_count":141},{"id":"2210.06726","title":"Explanations from Large Language Models Make Small Reasoners Better","created":"2022-10-13","cited_by_count":124},{"id":"2005.00115","title":"Learning to Faithfully Rationalize by Construction","created":"2020-04-30","cited_by_count":113},{"id":"1611.07270","title":"Investigating the influence of noise and distractors on the interpretation of neural networks","created":"2016-11-22","cited_by_count":54},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47},{"id":"2010.04736","title":"Evaluating and Characterizing Human Rationales","created":"2020-10-09","cited_by_count":36},{"id":"2203.07559","title":"On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency","created":"2022-03-14","cited_by_count":31},{"id":"2110.07596","title":"Retrieval-guided Counterfactual Generation for QA","created":"2021-10-14","cited_by_count":29},{"id":"2305.19249","title":"Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models","created":"2023-05-30","cited_by_count":29},{"id":"2203.00056","title":"An Empirical Study on Explanations in Out-of-Domain Settings","created":"2022-02-28","cited_by_count":21},{"id":"2104.04515","title":"Connecting Attributions and QA Model Behavior on Realistic Counterfactuals","created":"2021-04-09","cited_by_count":20},{"id":"2110.07586","title":"Can Explanations Be Useful for Calibrating Black Box Models?","created":"2021-10-14","cited_by_count":20},{"id":"2109.07022","title":"How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?","created":"2021-09-14","cited_by_count":19},{"id":"2205.04559","title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","created":"2022-05-09","cited_by_count":13},{"id":"2206.13757","title":"Flexible text generation for counterfactual fairness probing","created":"2022-06-28","cited_by_count":13},{"id":"2009.05167","title":"Accelerating Real-Time Question Answering via Question Generation","created":"2020-09-10","cited_by_count":11},{"id":"2211.03041","title":"Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates","created":"2022-11-06","cited_by_count":7}],"next_cursor":null}