{"total":60,"rows":[{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251,"area":"agents"},{"id":"2109.08535","title":"Simple Entity-Centric Questions Challenge Dense Retrievers","created":"2021-09-17","cited_by_count":140,"area":null},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138,"area":null},{"id":"2406.13629","title":"InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales","created":"2024-06-19","cited_by_count":101,"area":"rag"},{"id":"2301.01820","title":"InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval","created":"2023-01-04","cited_by_count":73,"area":null},{"id":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60,"area":null},{"id":"2107.11976","title":"One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval","created":"2021-07-26","cited_by_count":46,"area":null},{"id":"2112.07708","title":"Learning to Retrieve Passages without Supervision","created":"2021-12-14","cited_by_count":46,"area":null},{"id":"2104.05740","title":"A Replication Study of Dense Passage Retriever","created":"2021-04-12","cited_by_count":37,"area":null},{"id":"2401.07883","title":"The Chronicles of RAG: The Retriever, the Chunk and the Generator","created":"2024-01-15","cited_by_count":34,"area":"rag"},{"id":"2406.14644","title":"Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation","created":"2024-06-20","cited_by_count":30,"area":null},{"id":"2304.04358","title":"WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus","created":"2023-04-10","cited_by_count":29,"area":null},{"id":"2103.02280","title":"Simplified Data Wrangling with ir_datasets","created":"2021-03-03","cited_by_count":27,"area":null},{"id":"2203.03367","title":"Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2105.05686","title":"Yes, BM25 is a Strong Baseline for Legal Case Retrieval","created":"2021-04-26","cited_by_count":24,"area":null},{"id":"2405.13179","title":"RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts","created":"2024-05-21","cited_by_count":23,"area":"rag"},{"id":"2212.06121","title":"In Defense of Cross-Encoders for Zero-Shot Retrieval","created":"2022-12-12","cited_by_count":21,"area":null},{"id":"2201.07745","title":"Improving Biomedical Information Retrieval with Neural Retrievers","created":"2022-01-19","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":"2202.07280","title":"Saving Dense Retriever from Shortcut Dependency in Conversational Search","created":"2022-02-15","cited_by_count":19,"area":null},{"id":"2502.20640","title":"LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation","created":"2025-02-28","cited_by_count":19,"area":"rag"},{"id":"2206.02873","title":"No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval","created":"2022-06-06","cited_by_count":17,"area":null},{"id":"2406.00231","title":"LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking","created":"2024-05-31","cited_by_count":16,"area":null},{"id":"2406.10991","title":"Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers","created":"2024-06-16","cited_by_count":15,"area":"alignment"},{"id":"2207.06220","title":"Improving Wikipedia Verifiability with AI","created":"2022-07-08","cited_by_count":11,"area":null},{"id":"2212.05276","title":"Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verification","created":"2022-12-10","cited_by_count":11,"area":null},{"id":"2507.06956","title":"Investigating the Robustness of Retrieval-Augmented Generation at the Query Level","created":"2025-07-09","cited_by_count":11,"area":"rag"},{"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":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2110.01599","title":"Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering","created":"2021-10-04","cited_by_count":8,"area":null},{"id":"2310.16568","title":"1-PAGER: One Pass Answer Generation and Evidence Retrieval","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2503.23294","title":"Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference","created":"2025-03-30","cited_by_count":5,"area":"inference"},{"id":"2511.01386","title":"RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets","created":"2025-11-03","cited_by_count":5,"area":"rag"},{"id":"2603.14864","title":"Shopping Companion: Benchmarking and Training LLM Agents for Long-Horizon Preference-Grounded E-Commerce Tasks","created":"2026-03-16","cited_by_count":5,"area":"agents"},{"id":"2510.14660","title":"An Efficient Rubric-based Generative Verifier for Search-Augmented LLMs","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2311.02616","title":"Divide & Conquer for Entailment-aware Multi-hop Evidence Retrieval","created":"2023-11-05","cited_by_count":3,"area":null},{"id":"2505.10870","title":"Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate","created":"2025-05-16","cited_by_count":3,"area":"lr"},{"id":"2510.17139","title":"Rethinking On-policy Optimization for Query Augmentation","created":"2025-10-20","cited_by_count":3,"area":"lr"},{"id":"2204.07002","title":"XLMRQA: Open-Domain Question Answering on Vietnamese Wikipedia-based Textual Knowledge Source","created":"2022-04-14","cited_by_count":2,"area":null},{"id":"2211.16029","title":"Diverse Multi-Answer Retrieval with Determinantal Point Processes","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2408.16032","title":"An Extremely Data-efficient and Generative LLM-based Reinforcement Learning Agent for Recommenders","created":"2024-08-28","cited_by_count":2,"area":"agents"},{"id":"2606.25530","title":"Evaluating LLMs on Real-World Software Performance Optimization","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2109.11085","title":"Towards Universal Dense Retrieval for Open-domain Question Answering","created":"2021-09-23","cited_by_count":1,"area":null},{"id":"2206.12993","title":"Are We There Yet? A Decision Framework for Replacing Term Based Retrieval with Dense Retrieval Systems","created":"2022-06-26","cited_by_count":1,"area":null},{"id":"2207.01940","title":"MIA 2022 Shared Task Submission: Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answering","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2210.14837","title":"NeuralSearchX: Serving a Multi-billion-parameter Reranker for Multilingual Metasearch at a Low Cost","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2607.26497","title":"BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms","created":"2026-07-29","cited_by_count":1,"area":"rag"},{"id":"2202.03120","title":"To Tune or Not To Tune? Zero-shot Models for Legal Case Entailment","created":"2022-02-07","cited_by_count":0,"area":null},{"id":"2305.18977","title":"Cross Encoding as Augmentation: Towards Effective Educational Text Classification","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2505.16631","title":"MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2511.00875","title":"Controlling Gender Bias in Retrieval via a Backpack Architecture","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2511.04700","title":"Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation","created":"2025-11-01","cited_by_count":0,"area":"rag"},{"id":"2512.00267","title":"Trification: A Comprehensive Tree-based Strategy Planner and Structural Verification for Fact-Checking","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2601.09937","title":"From SERPs to Agents: A Platform for Comparative Studies of Information Interaction","created":"2026-01-14","cited_by_count":0,"area":"agents"},{"id":"2601.21208","title":"When should I search more: Adaptive Complex Query Optimization with Reinforcement Learning","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2604.08834","title":"BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2604.14389","title":"BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.18776","title":"Mask-to-Correct$^+$: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.31575","title":"SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.10621","title":"STORM: Stepwise Token Optimization with Reward-Guided Beam Search","created":"2026-06-09","cited_by_count":0,"area":null}],"next_cursor":null}