{"total":56,"rows":[{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297,"area":"agents"},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2401.03205","title":"The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models","created":"2024-01-06","cited_by_count":88,"area":null},{"id":"2407.01370","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","created":"2024-07-01","cited_by_count":87,"area":"rag"},{"id":"2504.13079","title":"Retrieval-Augmented Generation with Conflicting Evidence","created":"2025-04-17","cited_by_count":63,"area":"rag"},{"id":"2311.09533","title":"Effective Large Language Model Adaptation for Improved Grounding and Citation Generation","created":"2023-11-16","cited_by_count":45,"area":null},{"id":"2502.01113","title":"GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation","created":"2025-02-03","cited_by_count":40,"area":"rag"},{"id":"2411.10666","title":"SAM Decoding: Speculative Decoding via Suffix Automaton","created":"2024-11-16","cited_by_count":39,"area":"inference"},{"id":"2406.16828","title":"Ragnar\\\"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track","created":"2024-06-24","cited_by_count":32,"area":"rag"},{"id":"2406.19741","title":"ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning","created":"2024-06-28","cited_by_count":27,"area":"lr"},{"id":"2402.15089","title":"AttributionBench: How Hard is Automatic Attribution Evaluation?","created":"2024-02-23","cited_by_count":26,"area":null},{"id":"2410.03227","title":"ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering","created":"2024-10-04","cited_by_count":26,"area":"lr"},{"id":"2405.13622","title":"Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation","created":"2024-05-22","cited_by_count":25,"area":"rag"},{"id":"2405.17980","title":"Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering","created":"2024-05-28","cited_by_count":25,"area":null},{"id":"2403.18381","title":"Improving Attributed Text Generation of Large Language Models via Preference Learning","created":"2024-03-27","cited_by_count":23,"area":"alignment"},{"id":"2412.15235","title":"OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models","created":"2024-12-12","cited_by_count":23,"area":"rag"},{"id":"2402.02008","title":"How well do LLMs cite relevant medical references? An evaluation framework and analyses","created":"2024-02-03","cited_by_count":21,"area":null},{"id":"2406.16469","title":"Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM Collaboration","created":"2024-06-24","cited_by_count":19,"area":"mllm"},{"id":"2412.18004","title":"Correctness is not Faithfulness in RAG Attributions","created":"2024-12-23","cited_by_count":18,"area":null},{"id":"2401.14640","title":"Can LLMs Evaluate Complex Attribution in QA? Automatic Benchmarking using Knowledge Graphs","created":"2024-01-26","cited_by_count":17,"area":null},{"id":"2310.13571","title":"Why Can Large Language Models Generate Correct Chain-of-Thoughts?","created":"2023-10-20","cited_by_count":16,"area":"lr"},{"id":"2410.13716","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","created":"2024-10-17","cited_by_count":14,"area":"rag"},{"id":"2406.13124","title":"Learning to Generate Answers with Citations via Factual Consistency Models","created":"2024-06-19","cited_by_count":13,"area":null},{"id":"2408.04568","title":"Learning Fine-Grained Grounded Citations for Attributed Large Language Models","created":"2024-08-08","cited_by_count":13,"area":null},{"id":"2401.08699","title":"On Image Search in Histopathology","created":"2024-01-14","cited_by_count":12,"area":null},{"id":"2403.03194","title":"MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2308.07213","title":"Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AI","created":"2023-08-14","cited_by_count":9,"area":null},{"id":"2503.13565","title":"ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts","created":"2025-03-17","cited_by_count":9,"area":"inference"},{"id":"2604.14572","title":"Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG","created":"2026-04-16","cited_by_count":7,"area":"rag"},{"id":"2406.06938","title":"Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges","created":"2024-06-11","cited_by_count":5,"area":null},{"id":"2410.02115","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2510.10161","title":"Large Language Model Sourcing: A Survey","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2402.07770","title":"Had enough of experts? Quantitative knowledge retrieval from large language models","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2410.11217","title":"On the Capacity of Citation Generation by Large Language Models","created":"2024-10-15","cited_by_count":2,"area":"rag"},{"id":"2504.15689","title":"The Viability of Crowdsourcing for RAG Evaluation","created":"2025-04-22","cited_by_count":2,"area":"rag"},{"id":"2506.17585","title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2601.02917","title":"RAL2M: Retrieval Augmented Learning-To-Match Against Hallucination in Compliance-Guaranteed Service Systems","created":"2026-01-06","cited_by_count":2,"area":"rag"},{"id":"2603.07179","title":"Retrieving Minimal and Sufficient Reasoning Subgraphs with Graph Foundation Models for Path-aware GraphRAG","created":"2026-03-07","cited_by_count":2,"area":"rag"},{"id":"2410.12380","title":"Evaluation of Attribution Bias in Generator-Aware Retrieval-Augmented Large Language Models","created":"2024-10-16","cited_by_count":1,"area":"rag"},{"id":"2411.02448","title":"Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models","created":"2024-11-03","cited_by_count":1,"area":null},{"id":"2502.00989","title":"ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution","created":"2025-02-03","cited_by_count":1,"area":"agents"},{"id":"2505.12621","title":"SAFE: Improving LLM Systems using Sentence-Level In-generation Attribution","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2507.18857","title":"PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning","created":"2025-07-25","cited_by_count":1,"area":"lr"},{"id":"2602.11304","title":"CryptoAnalystBench: Failures in Multi-Tool Long-Form LLM Analysis","created":"2026-02-11","cited_by_count":1,"area":"agents"},{"id":"2606.16817","title":"Understanding the Behaviors of Environment-aware Information Retrieval","created":"2026-06-15","cited_by_count":1,"area":"rag"},{"id":"2410.17112","title":"Enhancing Answer Attribution for Faithful Text Generation with Large Language Models","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2501.03491","title":"Can LLMs Ask Good Questions?","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2508.08942","title":"Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokens","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2508.09072","title":"READER: Retrieval-Assisted Drafter for Efficient LLM Inference","created":"2025-08-12","cited_by_count":0,"area":"inference"},{"id":"2508.15085","title":"LongRecall: A Structured Approach for Robust Recall Evaluation in Long-Form Text","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.02241","title":"LLMs for LLMs: A Structured Prompting Methodology for Long Legal Documents","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.06426","title":"FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.20303","title":"Citation Failure: Definition, Analysis and Efficient Mitigation","created":"2025-10-23","cited_by_count":0,"area":"rag"},{"id":"2601.03669","title":"eTracer: Polarity-Aware Evidence Grounding","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2607.28397","title":"GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation","created":"2026-07-30","cited_by_count":0,"area":"rag"},{"id":"2609.00796","title":"SFAD: Speculative Factuality-Aware Decoding","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}