{"list":"other","total":71,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"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":"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":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"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":"2306.17563","title":"Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting","created":"2023-06-30","cited_by_count":307},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2202.01279","title":"PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts","created":"2022-02-02","cited_by_count":289},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249},{"id":"2206.02336","title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","created":"2022-06-06","cited_by_count":233},{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232},{"id":"2212.10001","title":"Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters","created":"2022-12-20","cited_by_count":222},{"id":"2305.10142","title":"Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback","created":"2023-05-17","cited_by_count":207},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125},{"id":"2306.03872","title":"Deductive Verification of Chain-of-Thought Reasoning","created":"2023-06-06","cited_by_count":124},{"id":"2207.00747","title":"Rationale-Augmented Ensembles in Language Models","created":"2022-07-02","cited_by_count":111},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92},{"id":"2307.08678","title":"Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations","created":"2023-07-17","cited_by_count":85},{"id":"2111.08284","title":"Few-Shot Self-Rationalization with Natural Language Prompts","created":"2021-11-16","cited_by_count":83},{"id":"2305.08298","title":"Symbol tuning improves in-context learning in language models","created":"2023-05-15","cited_by_count":75},{"id":"2305.13735","title":"Aligning Large Language Models through Synthetic Feedback","created":"2023-05-23","cited_by_count":75},{"id":"2005.00652","title":"An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction","created":"2020-05-01","cited_by_count":69},{"id":"2309.02144","title":"Making Large Language Models Better Reasoners with Alignment","created":"2023-09-05","cited_by_count":63},{"id":"2302.00618","title":"Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models","created":"2023-02-01","cited_by_count":61},{"id":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56},{"id":"2305.11426","title":"Post Hoc Explanations of Language Models Can Improve Language Models","created":"2023-05-19","cited_by_count":50},{"id":"2104.08731","title":"Can NLI Models Verify QA Systems' Predictions?","created":"2021-04-18","cited_by_count":46},{"id":"1605.04469","title":"Rationale-Augmented Convolutional Neural Networks for Text Classification","created":"2016-05-14","cited_by_count":39},{"id":"2305.07095","title":"Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales","created":"2023-05-11","cited_by_count":37},{"id":"2212.09257","title":"PromptBoosting: Black-Box Text Classification with Ten Forward Passes","created":"2022-12-19","cited_by_count":36},{"id":"2305.14934","title":"GRACE: Discriminator-Guided Chain-of-Thought Reasoning","created":"2023-05-24","cited_by_count":35},{"id":"2011.05268","title":"Towards Interpretable Natural Language Understanding with Explanations as Latent Variables","created":"2020-10-24","cited_by_count":30},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25},{"id":"2210.04982","title":"REV: Information-Theoretic Evaluation of Free-Text Rationales","created":"2022-10-10","cited_by_count":22},{"id":"2302.05852","title":"\"Why is this misleading?\": Detecting News Headline Hallucinations with Explanations","created":"2023-02-12","cited_by_count":17},{"id":"2209.06995","title":"Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach","created":"2022-09-15","cited_by_count":16},{"id":"2206.11083","title":"Investigating the Benefits of Free-Form Rationales","created":"2022-05-25","cited_by_count":13},{"id":"2302.04813","title":"Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting","created":"2023-02-09","cited_by_count":12},{"id":"2306.08042","title":"FLamE: Few-shot Learning from Natural Language Explanations","created":"2023-06-13","cited_by_count":10}],"next_cursor":null}