{"list":"other","total":51,"rows":[{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"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":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578},{"id":"2309.15217","title":"Ragas: Automated Evaluation of Retrieval Augmented Generation","created":"2023-09-26","cited_by_count":418},{"id":"2003.06713","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","created":"2020-03-14","cited_by_count":376},{"id":"2304.09542","title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","created":"2023-04-19","cited_by_count":360},{"id":"2003.07820","title":"Overview of the TREC 2019 deep learning track","created":"2020-03-17","cited_by_count":286},{"id":"2401.14887","title":"The Power of Noise: Redefining Retrieval for RAG Systems","created":"2024-01-26","cited_by_count":281},{"id":"2310.08319","title":"Fine-Tuning LLaMA for Multi-Stage Text Retrieval","created":"2023-10-12","cited_by_count":272},{"id":"2311.09476","title":"ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems","created":"2023-11-16","cited_by_count":265},{"id":"2407.12883","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","created":"2024-07-16","cited_by_count":158},{"id":"2312.02724","title":"RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!","created":"2023-12-05","cited_by_count":155},{"id":"2210.10634","title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","created":"2022-10-12","cited_by_count":115},{"id":"2511.19399","title":"DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research","created":"2025-11-24","cited_by_count":114},{"id":"2305.02156","title":"Zero-Shot Listwise Document Reranking with a Large Language Model","created":"2023-05-03","cited_by_count":82},{"id":"2404.10981","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","created":"2024-04-17","cited_by_count":77},{"id":"2309.15088","title":"RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models","created":"2023-09-26","cited_by_count":70},{"id":"2503.06034","title":"Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning","created":"2025-03-08","cited_by_count":60},{"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},{"id":"2509.00496","title":"ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics","created":"2025-08-30","cited_by_count":49},{"id":"2508.07050","title":"ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability","created":"2025-08-09","cited_by_count":42},{"id":"2510.26768","title":"AMO-Bench: Large Language Models Still Struggle in High School Math Competitions","created":"2025-10-30","cited_by_count":38},{"id":"2406.11194","title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","created":"2024-06-17","cited_by_count":34},{"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},{"id":"2505.20046","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","created":"2025-05-26","cited_by_count":24},{"id":"2502.19870","title":"MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge","created":"2025-02-27","cited_by_count":23},{"id":"2603.25133","title":"RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following","created":"2026-03-26","cited_by_count":20},{"id":"2505.19509","title":"Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models","created":"2025-05-26","cited_by_count":19},{"id":"2406.16332","title":"DemoRank: Selecting Effective Demonstrations for Large Language Models in Ranking Task","created":"2024-06-24","cited_by_count":17},{"id":"2507.06838","title":"Shifting from Ranking to Set Selection for Retrieval Augmented Generation","created":"2025-07-09","cited_by_count":15},{"id":"2511.02650","title":"Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models","created":"2025-11-04","cited_by_count":13},{"id":"2503.23427","title":"CoRanking: Collaborative Ranking with Small and Large Ranking Agents","created":"2025-03-30","cited_by_count":10},{"id":"2412.14574","title":"Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models","created":"2024-12-19","cited_by_count":8},{"id":"2505.24449","title":"When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations","created":"2025-05-30","cited_by_count":7},{"id":"2510.19457","title":"MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models","created":"2025-10-22","cited_by_count":7},{"id":"2604.11778","title":"General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks","created":"2026-04-13","cited_by_count":6},{"id":"2603.15117","title":"MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledge","created":"2026-03-16","cited_by_count":5},{"id":"2601.11273","title":"Rank4Gen: RAG-Preference-Aligned Document Set Selection and Ranking","created":"2026-01-16","cited_by_count":4},{"id":"2607.16609","title":"Can Multimodal Large Language Models Understand OCT?","created":"2026-07-18","cited_by_count":3},{"id":"2603.24204","title":"SumRank: Aligning Summarization Models for Long-Document Listwise Reranking","created":"2026-03-25","cited_by_count":2},{"id":"2511.09545","title":"Practical RAG Evaluation: A Rarity-Aware Set-Based Metric and Cost-Latency-Quality Trade-offs","created":"2025-11-12","cited_by_count":1}],"next_cursor":null}