{"list":"other","total":56,"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"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":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"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":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2402.01622","title":"TravelPlanner: A Benchmark for Real-World Planning with Language Agents","created":"2024-02-02","cited_by_count":392},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2310.12823","title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","created":"2023-10-19","cited_by_count":338},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282},{"id":"2303.05398","title":"MathPrompter: Mathematical Reasoning using Large Language Models","created":"2023-03-04","cited_by_count":236},{"id":"2301.13808","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","created":"2023-01-31","cited_by_count":178},{"id":"1909.05398","title":"Interactive Fiction Games: A Colossal Adventure","created":"2019-09-11","cited_by_count":168},{"id":"2308.07921","title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","created":"2023-08-15","cited_by_count":166},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"2308.06259","title":"Self-Alignment with Instruction Backtranslation","created":"2023-08-11","cited_by_count":151},{"id":"2402.14830","title":"Orca-Math: Unlocking the potential of SLMs in Grade School Math","created":"2024-02-16","cited_by_count":151},{"id":"2311.05657","title":"Agent Lumos: Unified and Modular Training for Open-Source Language Agents","created":"2023-11-09","cited_by_count":72},{"id":"2210.12810","title":"Code4Struct: Code Generation for Few-Shot Event Structure Prediction","created":"2022-10-23","cited_by_count":70},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33},{"id":"2402.01469","title":"AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback","created":"2024-02-02","cited_by_count":25},{"id":"2406.19934","title":"From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis","created":"2024-06-28","cited_by_count":17},{"id":"2404.00614","title":"Learning to Plan for Language Modeling from Unlabeled Data","created":"2024-03-31","cited_by_count":12}],"next_cursor":null}