{"list":"other","total":103,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"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":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"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":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"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":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"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":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"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":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"2403.02691","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","created":"2024-03-05","cited_by_count":538},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398},{"id":"2306.05301","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","created":"2023-06-08","cited_by_count":393},{"id":"2308.15363","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","created":"2023-08-29","cited_by_count":385},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"1307.5336","title":"Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts","created":"2013-07-19","cited_by_count":310},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"id":"2307.06135","title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","created":"2023-07-12","cited_by_count":294},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266},{"id":"2004.07347","title":"HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data","created":"2020-04-15","cited_by_count":264},{"id":"2310.17389","title":"ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation","created":"2023-10-26","cited_by_count":231},{"id":"2402.05044","title":"SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models","created":"2024-02-07","cited_by_count":228},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2306.05443","title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","created":"2023-06-08","cited_by_count":222},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215},{"id":"2205.12689","title":"Large Language Models are Few-Shot Clinical Information Extractors","created":"2022-05-25","cited_by_count":207},{"id":"2304.03439","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","created":"2023-04-07","cited_by_count":202},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202},{"id":"2011.03088","title":"HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification","created":"2020-11-05","cited_by_count":201},{"id":"2210.03849","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","created":"2022-10-07","cited_by_count":196},{"id":"2305.16653","title":"AdaPlanner: Adaptive Planning from Feedback with Language Models","created":"2023-05-26","cited_by_count":196},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186},{"id":"1709.04071","title":"Variational Reasoning for Question Answering with Knowledge Graph","created":"2017-09-12","cited_by_count":170},{"id":"2308.00436","title":"SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning","created":"2023-08-01","cited_by_count":159},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152},{"id":"2306.03901","title":"ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory","created":"2023-06-06","cited_by_count":140},{"id":"2312.02010","title":"Towards Learning a Generalist Model for Embodied Navigation","created":"2023-12-04","cited_by_count":138},{"id":"2404.05993","title":"AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts","created":"2024-04-09","cited_by_count":136},{"id":"2304.02015","title":"How well do Large Language Models perform in Arithmetic tasks?","created":"2023-03-16","cited_by_count":130},{"id":"2010.12773","title":"Structure-Grounded Pretraining for Text-to-SQL","created":"2020-10-24","cited_by_count":126},{"id":"2305.07609","title":"Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation","created":"2023-05-12","cited_by_count":114},{"id":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107},{"id":"2403.05156","title":"On Protecting the Data Privacy of Large Language Models (LLMs): A Survey","created":"2024-03-08","cited_by_count":96},{"id":"2305.06849","title":"WebCPM: Interactive Web Search for Chinese Long-form Question Answering","created":"2023-05-11","cited_by_count":93},{"id":"2305.12002","title":"XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters","created":"2023-05-19","cited_by_count":92},{"id":"2307.09705","title":"CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility","created":"2023-07-19","cited_by_count":85},{"id":"2009.04202","title":"Impact of News on the Commodity Market: Dataset and Results","created":"2020-09-09","cited_by_count":80},{"id":"2402.09267","title":"Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation","created":"2024-02-14","cited_by_count":80},{"id":"2402.02315","title":"A Survey of Large Language Models in Finance (FinLLMs)","created":"2024-02-04","cited_by_count":79},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75},{"id":"2302.06100","title":"Can GPT-3 Perform Statutory Reasoning?","created":"2023-02-13","cited_by_count":73},{"id":"2210.12023","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","created":"2022-10-21","cited_by_count":68},{"id":"2403.13031","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","created":"2024-03-19","cited_by_count":68},{"id":"2402.13249","title":"TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization","created":"2024-02-20","cited_by_count":66},{"id":"2107.00285","title":"iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis","created":"2021-07-01","cited_by_count":63},{"id":"2005.05257","title":"A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering","created":"2020-05-11","cited_by_count":62},{"id":"2308.03427","title":"TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage","created":"2023-08-07","cited_by_count":55},{"id":"2304.10513","title":"Why Does ChatGPT Fall Short in Providing Truthful Answers?","created":"2023-04-20","cited_by_count":54},{"id":"2306.01248","title":"How Ready are Pre-trained Abstractive Models and LLMs for Legal Case Judgement Summarization?","created":"2023-06-02","cited_by_count":43},{"id":"2310.06498","title":"A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection","created":"2023-10-10","cited_by_count":42},{"id":"2306.06085","title":"Trapping LLM Hallucinations Using Tagged Context Prompts","created":"2023-06-09","cited_by_count":34},{"id":"2402.10412","title":"Measuring and Reducing LLM Hallucination without Gold-Standard Answers","created":"2024-02-16","cited_by_count":31},{"id":"2211.14228","title":"GPT-3-driven pedagogical agents for training children's curious question-asking skills","created":"2022-11-25","cited_by_count":29},{"id":"2310.11053","title":"Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning","created":"2023-10-17","cited_by_count":26},{"id":"1804.00619","title":"Modeling Semantic Plausibility by Injecting World Knowledge","created":"2018-04-02","cited_by_count":24},{"id":"2209.11830","title":"Multiple-Choice Question Generation: Towards an Automated Assessment Framework","created":"2022-09-23","cited_by_count":23},{"id":"2403.05916","title":"GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computing","created":"2024-03-09","cited_by_count":22},{"id":"2304.13148","title":"Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection","created":"2023-04-25","cited_by_count":18}],"next_cursor":"100"}