{"list":"other","total":83,"rows":[{"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":"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":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"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":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"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":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"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":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"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":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"2001.09977","title":"Towards a Human-like Open-Domain Chatbot","created":"2020-01-27","cited_by_count":470},{"id":"2105.07624","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","created":"2021-05-17","cited_by_count":408},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388},{"id":"1608.01413","title":"Solving General Arithmetic Word Problems","created":"2016-08-04","cited_by_count":360},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2212.09196","title":"Emergent Analogical Reasoning in Large Language Models","created":"2022-12-19","cited_by_count":240},{"id":"2206.02336","title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","created":"2022-06-06","cited_by_count":233},{"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":"2212.08061","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","created":"2022-12-15","cited_by_count":194},{"id":"2005.04611","title":"How Context Affects Language Models' Factual Predictions","created":"2020-05-10","cited_by_count":181},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169},{"id":"2304.09797","title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","created":"2023-04-19","cited_by_count":147},{"id":"2301.00303","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","created":"2022-12-31","cited_by_count":145},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138},{"id":"2207.00747","title":"Rationale-Augmented Ensembles in Language Models","created":"2022-07-02","cited_by_count":111},{"id":"2305.17306","title":"Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance","created":"2023-05-26","cited_by_count":102},{"id":"2306.00924","title":"Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker","created":"2023-06-01","cited_by_count":95},{"id":"2206.02369","title":"Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation","created":"2022-06-06","cited_by_count":94},{"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":"2210.05359","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","created":"2022-10-11","cited_by_count":84},{"id":"2210.16257","title":"Solving Math Word Problems via Cooperative Reasoning induced Language Models","created":"2022-10-28","cited_by_count":77},{"id":"2306.06427","title":"Boosting Language Models Reasoning with Chain-of-Knowledge Prompting","created":"2023-06-10","cited_by_count":77},{"id":"2303.02913","title":"OpenICL: An Open-Source Framework for In-context Learning","created":"2023-03-06","cited_by_count":51},{"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":"1601.00372","title":"Mutual Information and Diverse Decoding Improve Neural Machine Translation","created":"2016-01-04","cited_by_count":35},{"id":"2305.14333","title":"Automatic Model Selection with Large Language Models for Reasoning","created":"2023-05-23","cited_by_count":35},{"id":"2211.04256","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","created":"2022-11-08","cited_by_count":5},{"id":"2302.14286","title":"HugNLP: A Unified and Comprehensive Library for Natural Language Processing","created":"2023-02-28","cited_by_count":1}],"next_cursor":null}