{"list":"other","total":89,"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":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"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":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"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":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"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":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452},{"id":"2501.07301","title":"The Lessons of Developing Process Reward Models in Mathematical Reasoning","created":"2025-01-13","cited_by_count":415},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384},{"id":"2507.17746","title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","created":"2025-07-23","cited_by_count":366},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341},{"id":"2404.18796","title":"Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models","created":"2024-04-29","cited_by_count":326},{"id":"2402.00157","title":"Large Language Models for Mathematical Reasoning: Progresses and Challenges","created":"2024-01-31","cited_by_count":284},{"id":"2406.07791","title":"Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge","created":"2024-06-12","cited_by_count":269},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264},{"id":"2501.09136","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG","created":"2025-01-15","cited_by_count":249},{"id":"2305.14283","title":"Query Rewriting for Retrieval-Augmented Large Language Models","created":"2023-05-23","cited_by_count":213},{"id":"2505.04588","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","created":"2025-05-07","cited_by_count":208},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184},{"id":"2501.17399","title":"MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs","created":"2025-01-29","cited_by_count":180},{"id":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170},{"id":"2405.13576","title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","created":"2024-05-22","cited_by_count":166},{"id":"2310.06117","title":"Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models","created":"2023-10-09","cited_by_count":159},{"id":"2404.00610","title":"RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation","created":"2024-03-31","cited_by_count":147},{"id":"2204.07931","title":"On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?","created":"2022-04-17","cited_by_count":138},{"id":"2211.14876","title":"Dense Text Retrieval based on Pretrained Language Models: A Survey","created":"2022-11-27","cited_by_count":136},{"id":"2507.18624","title":"Checklists Are Better Than Reward Models For Aligning Language Models","created":"2025-07-24","cited_by_count":128},{"id":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110},{"id":"2204.10757","title":"FaithDial: A Faithful Benchmark for Information-Seeking Dialogue","created":"2022-04-22","cited_by_count":109},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86},{"id":"2307.08678","title":"Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations","created":"2023-07-17","cited_by_count":85},{"id":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84},{"id":"2311.07466","title":"On Measuring Faithfulness or Self-consistency of Natural Language Explanations","created":"2023-11-13","cited_by_count":73},{"id":"2406.11050","title":"A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners","created":"2024-06-16","cited_by_count":73},{"id":"2501.08156","title":"Are DeepSeek R1 And Other Reasoning Models More Faithful?","created":"2025-01-14","cited_by_count":72},{"id":"2407.14482","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","created":"2024-07-19","cited_by_count":53},{"id":"2412.15280","title":"Context-DPO: Aligning Language Models for Context-Faithfulness","created":"2024-12-18","cited_by_count":50},{"id":"2504.14150","title":"Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations","created":"2025-04-19","cited_by_count":45},{"id":"2501.00332","title":"MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation","created":"2024-12-31","cited_by_count":44},{"id":"2402.16048","title":"How Likely Do LLMs with CoT Mimic Human Reasoning?","created":"2024-02-25","cited_by_count":34},{"id":"2407.04965","title":"Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression","created":"2024-07-06","cited_by_count":33},{"id":"2402.14897","title":"Chain-of-Thought Unfaithfulness as Disguised Accuracy","created":"2024-02-22","cited_by_count":28},{"id":"2506.21495","title":"Bridging Offline and Online Reinforcement Learning for LLMs","created":"2025-06-26","cited_by_count":25},{"id":"2404.08700","title":"DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs","created":"2024-04-10","cited_by_count":24},{"id":"2502.14822","title":"A Survey of Model Architectures in Information Retrieval","created":"2025-02-20","cited_by_count":20},{"id":"2402.11447","title":"In-Context Example Ordering Guided by Label Distributions","created":"2024-02-18","cited_by_count":12},{"id":"2411.07237","title":"Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries","created":"2024-11-11","cited_by_count":12},{"id":"2505.23945","title":"A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models","created":"2025-05-29","cited_by_count":12},{"id":"2312.14335","title":"Context-aware Decoding Reduces Hallucination in Query-focused Summarization","created":"2023-12-21","cited_by_count":11},{"id":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","cited_by_count":10},{"id":"2507.08336","title":"Distillation versus Contrastive Learning: How to Train Your Rerankers","created":"2025-07-11","cited_by_count":6},{"id":"2510.04695","title":"Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents","created":"2025-10-06","cited_by_count":4}],"next_cursor":null}