{"total":307,"rows":[{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919,"area":"agents"},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2308.07107","title":"Large Language Models for Information Retrieval: A Survey","created":"2023-08-14","cited_by_count":331,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"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,"area":null},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2406.07155","title":"Scaling Large Language Model-based Multi-Agent Collaboration","created":"2024-06-11","cited_by_count":241,"area":"agents"},{"id":"2407.02485","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","created":"2024-07-02","cited_by_count":202,"area":"rag"},{"id":"2403.16950","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","created":"2024-03-25","cited_by_count":149,"area":"alignment"},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126,"area":null},{"id":"2404.11457","title":"Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era","created":"2024-04-17","cited_by_count":98,"area":null},{"id":"2308.08239","title":"MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation","created":"2023-08-16","cited_by_count":97,"area":null},{"id":"2402.01878","title":"LiPO: Listwise Preference Optimization through Learning-to-Rank","created":"2024-02-02","cited_by_count":96,"area":"alignment"},{"id":"2403.18771","title":"CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists","created":"2024-03-27","cited_by_count":94,"area":null},{"id":"2404.10981","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","created":"2024-04-17","cited_by_count":77,"area":"rag"},{"id":"2307.07889","title":"LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models","created":"2023-07-15","cited_by_count":71,"area":null},{"id":"2309.15088","title":"RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models","created":"2023-09-26","cited_by_count":70,"area":null},{"id":"2404.13081","title":"SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs","created":"2024-04-17","cited_by_count":67,"area":null},{"id":"2502.14902","title":"PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths","created":"2025-02-18","cited_by_count":61,"area":"rag"},{"id":"2503.06034","title":"Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning","created":"2025-03-08","cited_by_count":60,"area":"lr"},{"id":"2404.00579","title":"A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2312.17025","title":"Experiential Co-Learning of Software-Developing Agents","created":"2023-12-28","cited_by_count":57,"area":"agents"},{"id":"2310.09497","title":"A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models","created":"2023-10-14","cited_by_count":55,"area":null},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2311.07838","title":"LLatrieval: LLM-Verified Retrieval for Verifiable Generation","created":"2023-11-14","cited_by_count":52,"area":null},{"id":"2402.07314","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","created":"2024-02-11","cited_by_count":52,"area":"alignment"},{"id":"2406.11678","title":"TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy","created":"2024-06-17","cited_by_count":47,"area":null},{"id":"2412.02617","title":"Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback","created":"2024-12-03","cited_by_count":47,"area":"mllm"},{"id":"2404.00725","title":"The Larger the Better? Improved LLM Code-Generation via Budget Reallocation","created":"2024-03-31","cited_by_count":43,"area":null},{"id":"2506.22316","title":"Evaluating Scoring Bias in LLM-as-a-Judge","created":"2025-06-27","cited_by_count":43,"area":null},{"id":"2508.07050","title":"ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability","created":"2025-08-09","cited_by_count":42,"area":"lr"},{"id":"2412.01007","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","created":"2024-12-01","cited_by_count":37,"area":null},{"id":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2411.00142","title":"JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking","created":"2024-10-31","cited_by_count":34,"area":"lr"},{"id":"2503.05659","title":"A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval","created":"2025-03-07","cited_by_count":33,"area":"agents"},{"id":"2405.16884","title":"Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching","created":"2024-05-27","cited_by_count":32,"area":null},{"id":"2310.07712","title":"Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models","created":"2023-10-11","cited_by_count":31,"area":"lr"},{"id":"2402.17826","title":"Prediction-Powered Ranking of Large Language Models","created":"2024-02-27","cited_by_count":29,"area":null},{"id":"2406.14449","title":"APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking","created":"2024-06-20","cited_by_count":28,"area":null},{"id":"2406.18676","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","created":"2024-06-26","cited_by_count":27,"area":"rag"},{"id":"2406.11370","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","created":"2024-06-17","cited_by_count":25,"area":"alignment"},{"id":"2505.20046","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","created":"2025-05-26","cited_by_count":24,"area":"lr"},{"id":"2509.25085","title":"jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking","created":"2025-09-29","cited_by_count":24,"area":null},{"id":"2403.19216","title":"Are Large Language Models Good at Utility Judgments?","created":"2024-03-28","cited_by_count":22,"area":"rag"},{"id":"2405.05894","title":"Efficient LLM Comparative Assessment: a Product of Experts Framework for Pairwise Comparisons","created":"2024-05-09","cited_by_count":22,"area":null},{"id":"2505.02847","title":"Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models","created":"2025-05-01","cited_by_count":21,"area":"agents"},{"id":"2401.06532","title":"INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning","created":"2024-01-12","cited_by_count":20,"area":null},{"id":"2403.00784","title":"Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges","created":"2024-02-18","cited_by_count":20,"area":null},{"id":"2404.18185","title":"Ranked List Truncation for Large Language Model-based Re-Ranking","created":"2024-04-28","cited_by_count":20,"area":null},{"id":"2406.14848","title":"Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models","created":"2024-06-21","cited_by_count":20,"area":null},{"id":"2311.01555","title":"Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers","created":"2023-11-02","cited_by_count":19,"area":null},{"id":"2410.08851","title":"Measuring the Inconsistency of Large Language Models in Preferential Ranking","created":"2024-10-11","cited_by_count":19,"area":null},{"id":"2506.16507","title":"Robust Reward Modeling via Causal Rubrics","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2310.20158","title":"GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval","created":"2023-10-31","cited_by_count":18,"area":null},{"id":"2404.01012","title":"Query Performance Prediction using Relevance Judgments Generated by Large Language Models","created":"2024-04-01","cited_by_count":18,"area":null},{"id":"2401.04514","title":"Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search","created":"2024-01-09","cited_by_count":17,"area":null},{"id":"2404.03192","title":"Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2405.12363","title":"Question-Based Retrieval using Atomic Units for Enterprise RAG","created":"2024-05-20","cited_by_count":17,"area":"rag"},{"id":"2406.16332","title":"DemoRank: Selecting Effective Demonstrations for Large Language Models in Ranking Task","created":"2024-06-24","cited_by_count":17,"area":null},{"id":"2412.12559","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","created":"2024-12-17","cited_by_count":17,"area":"rag"},{"id":"2505.16967","title":"Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs","created":"2025-05-22","cited_by_count":17,"area":null},{"id":"2405.04219","title":"Iterative Experience Refinement of Software-Developing Agents","created":"2024-05-07","cited_by_count":16,"area":"agents"},{"id":"2406.00231","title":"LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking","created":"2024-05-31","cited_by_count":16,"area":null},{"id":"2406.12566","title":"RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation","created":"2024-06-18","cited_by_count":16,"area":"rag"},{"id":"2501.09186","title":"Guiding Retrieval using LLM-based Listwise Rankers","created":"2025-01-15","cited_by_count":16,"area":null},{"id":"2509.09498","title":"SEDM: Selective Self-Evolving Distributed Memory for Agents","created":"2025-09-11","cited_by_count":16,"area":null},{"id":"2601.06992","title":"FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering","created":"2026-01-11","cited_by_count":16,"area":null},{"id":"2402.14151","title":"BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives","created":"2024-02-21","cited_by_count":15,"area":null},{"id":"2404.16924","title":"A Survey of Generative Search and Recommendation in the Era of Large Language Models","created":"2024-04-25","cited_by_count":15,"area":null},{"id":"2503.19092","title":"Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation","created":"2025-03-24","cited_by_count":15,"area":null},{"id":"2505.07233","title":"DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation","created":"2025-05-12","cited_by_count":15,"area":"rag"},{"id":"2507.06838","title":"Shifting from Ranking to Set Selection for Retrieval Augmented Generation","created":"2025-07-09","cited_by_count":15,"area":"rag"},{"id":"2311.00687","title":"Improving Interpersonal Communication by Simulating Audiences with Language Models","created":"2023-11-01","cited_by_count":14,"area":null},{"id":"2312.02969","title":"Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2504.12558","title":"Benchmarking LLM-based Relevance Judgment Methods","created":"2025-04-17","cited_by_count":14,"area":null},{"id":"2309.06991","title":"Unsupervised Contrast-Consistent Ranking with Language Models","created":"2023-09-13","cited_by_count":13,"area":null},{"id":"2312.15746","title":"Large Language Models are Not Stable Recommender Systems","created":"2023-12-25","cited_by_count":13,"area":null},{"id":"2502.02464","title":"Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation","created":"2025-02-04","cited_by_count":13,"area":"rag"},{"id":"2502.15861","title":"C3AI: Crafting and Evaluating Constitutions for Constitutional AI","created":"2025-02-21","cited_by_count":13,"area":"alignment"},{"id":"2307.08303","title":"Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models","created":"2023-07-17","cited_by_count":12,"area":null},{"id":"2311.09175","title":"Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?","created":"2023-11-15","cited_by_count":12,"area":null},{"id":"2410.19218","title":"Taxonomy-guided Semantic Indexing for Academic Paper Search","created":"2024-10-25","cited_by_count":12,"area":null},{"id":"2501.17630","title":"Uncertainty Quantification and Decomposition for LLM-based Recommendation","created":"2025-01-29","cited_by_count":12,"area":null},{"id":"2504.07439","title":"LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking","created":"2025-04-10","cited_by_count":12,"area":null},{"id":"2509.16112","title":"CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion","created":"2025-09-19","cited_by_count":12,"area":"rag"},{"id":"2308.12519","title":"Rational Decision-Making Agent with Internalized Utility Judgment","created":"2023-08-24","cited_by_count":11,"area":"agents"},{"id":"2311.04694","title":"Evaluating Generative Ad Hoc Information Retrieval","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2403.19181","title":"Make Large Language Model a Better Ranker","created":"2024-03-28","cited_by_count":11,"area":null},{"id":"2404.01015","title":"PairEval: Open-domain Dialogue Evaluation with Pairwise Comparison","created":"2024-04-01","cited_by_count":11,"area":null},{"id":"2406.02886","title":"PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs","created":"2024-06-05","cited_by_count":11,"area":"distill"},{"id":"2501.06582","title":"ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting","created":"2025-01-11","cited_by_count":11,"area":null},{"id":"2508.16998","title":"DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation","created":"2025-08-23","cited_by_count":11,"area":"lr"},{"id":"2510.08783","title":"MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces","created":"2025-10-09","cited_by_count":11,"area":null},{"id":"2512.00968","title":"Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search","created":"2025-11-30","cited_by_count":11,"area":"lr"},{"id":"2311.07930","title":"It's All Relative! -- A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction","created":"2023-11-14","cited_by_count":10,"area":null},{"id":"2405.13131","title":"Atomic Self-Consistency for Better Long Form Generations","created":"2024-05-21","cited_by_count":10,"area":"lr"},{"id":"2503.23427","title":"CoRanking: Collaborative Ranking with Small and Large Ranking Agents","created":"2025-03-30","cited_by_count":10,"area":"agents"},{"id":"2311.07592","title":"Hallucination-minimized Data-to-answer Framework for Financial Decision-makers","created":"2023-11-09","cited_by_count":9,"area":null}],"next_cursor":"100"}