{"list":"other","total":108,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"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":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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":"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":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1711.00399","title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR","created":"2017-11-01","cited_by_count":1089},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"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":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422},{"id":"2302.14520","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","created":"2023-02-28","cited_by_count":420},{"id":"1509.06321","title":"Evaluating the visualization of what a Deep Neural Network has learned","created":"2015-09-21","cited_by_count":419},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361},{"id":"2104.14478","title":"Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation","created":"2021-04-29","cited_by_count":338},{"id":"2001.02114","title":"Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making","created":"2020-01-07","cited_by_count":281},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"2005.10608","title":"Unsupervised Quality Estimation for Neural Machine Translation","created":"2020-05-21","cited_by_count":211},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207},{"id":"2209.06243","title":"CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task","created":"2022-09-13","cited_by_count":207},{"id":"1708.08296","title":"Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models","created":"2017-08-28","cited_by_count":206},{"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":"2005.01831","title":"Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?","created":"2020-05-04","cited_by_count":190},{"id":"2212.07919","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","created":"2022-12-15","cited_by_count":177},{"id":"1909.03012","title":"One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques","created":"2019-09-06","cited_by_count":164},{"id":"2008.12009","title":"A Survey of Evaluation Metrics Used for NLG Systems","created":"2020-08-27","cited_by_count":164},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155},{"id":"2005.06676","title":"Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions","created":"2020-05-14","cited_by_count":144},{"id":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136},{"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":"2004.14564","title":"Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing","created":"2020-04-30","cited_by_count":115},{"id":"2303.13809","title":"Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models","created":"2023-03-24","cited_by_count":87},{"id":"2001.05871","title":"\"Why is 'Chicago' deceptive?\" Towards Building Model-Driven Tutorials for Humans","created":"2020-01-14","cited_by_count":86},{"id":"2304.00723","title":"Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: An Empirical Study","created":"2023-04-03","cited_by_count":85},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81},{"id":"2006.01067","title":"Aligning Faithful Interpretations with their Social Attribution","created":"2020-06-01","cited_by_count":79},{"id":"1912.00782","title":"The relationship between trust in AI and trustworthy machine learning technologies","created":"2019-11-27","cited_by_count":78},{"id":"1808.08866","title":"A Study of Reinforcement Learning for Neural Machine Translation","created":"2018-08-27","cited_by_count":74},{"id":"2106.15195","title":"Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers","created":"2021-06-29","cited_by_count":71},{"id":"2208.05309","title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","created":"2022-08-10","cited_by_count":61},{"id":"2011.01536","title":"TransQuest: Translation Quality Estimation with Cross-lingual Transformers","created":"2020-11-01","cited_by_count":59},{"id":"2103.11878","title":"BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation","created":"2021-03-22","cited_by_count":58},{"id":"2004.02015","title":"Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection","created":"2020-04-04","cited_by_count":57},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53},{"id":"2109.05771","title":"Perturbation CheckLists for Evaluating NLG Evaluation Metrics","created":"2021-09-13","cited_by_count":50},{"id":"2205.00978","title":"Quality-Aware Decoding for Neural Machine Translation","created":"2022-05-02","cited_by_count":49},{"id":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49},{"id":"2210.07626","title":"BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation","created":"2022-10-14","cited_by_count":48},{"id":"2009.05487","title":"The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples","created":"2020-09-11","cited_by_count":44},{"id":"2206.13289","title":"Analyzing Encoded Concepts in Transformer Language Models","created":"2022-06-27","cited_by_count":38},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38},{"id":"2005.01196","title":"On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation","created":"2020-05-03","cited_by_count":36},{"id":"2201.11176","title":"DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence","created":"2022-01-26","cited_by_count":36},{"id":"2210.13746","title":"DEMETR: Diagnosing Evaluation Metrics for Translation","created":"2022-10-25","cited_by_count":36},{"id":"2206.07023","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","created":"2022-06-14","cited_by_count":33},{"id":"1802.06924","title":"Teaching Categories to Human Learners with Visual Explanations","created":"2018-02-20","cited_by_count":30},{"id":"2110.04392","title":"The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results","created":"2021-10-08","cited_by_count":27},{"id":"2110.04399","title":"Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors","created":"2021-10-08","cited_by_count":25},{"id":"2210.15615","title":"ACES: Translation Accuracy Challenge Sets for Evaluating Machine Translation Metrics","created":"2022-10-27","cited_by_count":25},{"id":"2303.07610","title":"Exploring ChatGPT's Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences","created":"2023-03-14","cited_by_count":25},{"id":"1907.10739","title":"Visual Interaction with Deep Learning Models through Collaborative Semantic Inference","created":"2019-07-24","cited_by_count":24},{"id":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23},{"id":"2108.12197","title":"Translation Error Detection as Rationale Extraction","created":"2021-08-27","cited_by_count":22},{"id":"2301.08912","title":"Rationalization for Explainable NLP: A Survey","created":"2023-01-21","cited_by_count":22},{"id":"2306.04292","title":"Dear XAI Community, We Need to Talk! Fundamental Misconceptions in Current XAI Research","created":"2023-06-07","cited_by_count":22},{"id":"2010.05318","title":"TransQuest at WMT2020: Sentence-Level Direct Assessment","created":"2020-10-11","cited_by_count":20},{"id":"2204.10810","title":"Learning to Scaffold: Optimizing Model Explanations for Teaching","created":"2022-04-22","cited_by_count":20},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19},{"id":"2106.02208","title":"BERTTune: Fine-Tuning Neural Machine Translation with BERTScore","created":"2021-06-04","cited_by_count":18},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18},{"id":"2208.07316","title":"MENLI: Robust Evaluation Metrics from Natural Language Inference","created":"2022-08-15","cited_by_count":18},{"id":"2212.10179","title":"Toward Human-Like Evaluation for Natural Language Generation with Error Analysis","created":"2022-12-20","cited_by_count":18},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15},{"id":"2202.10062","title":"USCORE: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translation","created":"2022-02-21","cited_by_count":15},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15},{"id":"2205.11097","title":"A Fine-grained Interpretability Evaluation Benchmark for Neural NLP","created":"2022-05-23","cited_by_count":15},{"id":"2305.11806","title":"The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics","created":"2023-05-19","cited_by_count":15}],"next_cursor":"100"}