{"total":109,"rows":[{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341,"area":null},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151,"area":null},{"id":"2305.14536","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","created":"2023-05-23","cited_by_count":131,"area":"lr"},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107,"area":"alignment"},{"id":"2311.00059","title":"The Generative AI Paradox: \"What It Can Create, It May Not Understand\"","created":"2023-10-31","cited_by_count":98,"area":null},{"id":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84,"area":null},{"id":"2310.12808","title":"Model Merging by Uncertainty-Based Gradient Matching","created":"2023-10-19","cited_by_count":77,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2501.03468","title":"MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems","created":"2025-01-07","cited_by_count":51,"area":"rag"},{"id":"2305.13632","title":"Detecting and Mitigating Hallucinations in Multilingual Summarisation","created":"2023-05-23","cited_by_count":48,"area":null},{"id":"2409.12894","title":"VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation","created":"2024-09-19","cited_by_count":45,"area":"vla"},{"id":"2310.07289","title":"Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators","created":"2023-10-11","cited_by_count":43,"area":null},{"id":"2406.04175","title":"Confabulation: The Surprising Value of Large Language Model Hallucinations","created":"2024-06-06","cited_by_count":43,"area":null},{"id":"2310.03184","title":"Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference","created":"2023-10-04","cited_by_count":38,"area":"rag"},{"id":"2401.06796","title":"AI Hallucinations: A Misnomer Worth Clarifying","created":"2024-01-09","cited_by_count":34,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2301.04449","title":"Diving Deep into Modes of Fact Hallucinations in Dialogue Systems","created":"2023-01-11","cited_by_count":32,"area":null},{"id":"2310.01779","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","created":"2023-10-03","cited_by_count":32,"area":"mllm"},{"id":"2303.17574","title":"Elastic Weight Removal for Faithful and Abstractive Dialogue Generation","created":"2023-03-30","cited_by_count":29,"area":null},{"id":"2310.12086","title":"FactCHD: Benchmarking Fact-Conflicting Hallucination Detection","created":"2023-10-18","cited_by_count":29,"area":null},{"id":"2406.07070","title":"HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation","created":"2024-06-11","cited_by_count":27,"area":null},{"id":"2305.16519","title":"The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answering","created":"2023-05-25","cited_by_count":26,"area":null},{"id":"2405.14486","title":"RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models","created":"2024-05-23","cited_by_count":25,"area":null},{"id":"2508.08285","title":"The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2310.11648","title":"Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model","created":"2023-10-18","cited_by_count":21,"area":null},{"id":"2405.13684","title":"CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models","created":"2024-05-22","cited_by_count":18,"area":null},{"id":"2305.14718","title":"Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models","created":"2023-05-24","cited_by_count":17,"area":"alignment"},{"id":"2404.07461","title":"An Audit on the Perspectives and Challenges of Hallucinations in NLP","created":"2024-04-11","cited_by_count":17,"area":null},{"id":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2403.00896","title":"DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models","created":"2024-03-01","cited_by_count":15,"area":null},{"id":"2410.18359","title":"Improving Model Factuality with Fine-grained Critique-based Evaluator","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2303.09713","title":"CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos","created":"2023-03-17","cited_by_count":14,"area":null},{"id":"2309.06490","title":"Leveraging Large Language Models for Automated Dialogue Analysis","created":"2023-09-12","cited_by_count":14,"area":null},{"id":"2407.04693","title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","created":"2024-07-05","cited_by_count":14,"area":null},{"id":"2404.03745","title":"Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2507.07030","title":"UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations","created":"2025-07-09","cited_by_count":12,"area":null},{"id":"2305.12191","title":"Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs","created":"2023-05-20","cited_by_count":11,"area":null},{"id":"2311.09800","title":"$\\textit{Dial BeInfo for Faithfulness}$: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning","created":"2023-11-16","cited_by_count":9,"area":null},{"id":"2602.23184","title":"MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations","created":"2026-02-26","cited_by_count":9,"area":"rag"},{"id":"2205.09314","title":"Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2205.11505","title":"What Makes Data-to-Text Generation Hard for Pretrained Language Models?","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2410.14676","title":"SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment","created":"2024-10-18","cited_by_count":8,"area":"alignment"},{"id":"2305.17280","title":"Improved Instruction Ordering in Recipe-Grounded Conversation","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2405.20315","title":"ANAH: Analytical Annotation of Hallucinations in Large Language Models","created":"2024-05-30","cited_by_count":7,"area":null},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2311.08117","title":"Insights into Classifying and Mitigating LLMs' Hallucinations","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2504.18114","title":"Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection","created":"2025-04-25","cited_by_count":6,"area":null},{"id":"2505.21072","title":"Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation","created":"2025-05-27","cited_by_count":6,"area":"rag"},{"id":"2510.13272","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"id":"2310.18794","title":"Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2311.09467","title":"Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2502.16766","title":"ATEB: Evaluating and Improving Advanced NLP Tasks for Text Embedding Models","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2511.12693","title":"HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models","created":"2025-11-16","cited_by_count":5,"area":"mllm"},{"id":"2308.06488","title":"Generating Faithful Text From a Knowledge Graph with Noisy Reference Text","created":"2023-08-12","cited_by_count":4,"area":null},{"id":"2403.14578","title":"RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain","created":"2024-03-21","cited_by_count":4,"area":null},{"id":"2410.15297","title":"Redefining Proactivity for Information Seeking Dialogue","created":"2024-10-20","cited_by_count":4,"area":null},{"id":"2410.17477","title":"Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2210.17418","title":"Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model","created":"2022-10-31","cited_by_count":3,"area":null},{"id":"2405.10128","title":"Red Teaming Language Models for Processing Contradictory Dialogues","created":"2024-05-16","cited_by_count":3,"area":"safety"},{"id":"2502.08109","title":"HuDEx: Integrating Hallucination Detection and Explainability for Enhancing the Reliability of LLM responses","created":"2025-02-12","cited_by_count":3,"area":null},{"id":"2508.05283","title":"Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2509.07475","title":"HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2603.26567","title":"Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering","created":"2026-03-27","cited_by_count":3,"area":null},{"id":"2204.12681","title":"Building Knowledge-Grounded Dialogue Systems with Graph-Based Semantic Modeling","created":"2022-04-27","cited_by_count":2,"area":null},{"id":"2305.14658","title":"Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2307.07544","title":"A Dialogue System for Assessing Activities of Daily Living: Improving Consistency with Grounded Knowledge","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2503.14797","title":"FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2509.09360","title":"MetaRAG: Metamorphic Testing for Hallucination Detection in RAG Systems","created":"2025-09-11","cited_by_count":2,"area":"rag"},{"id":"2307.07255","title":"Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems","created":"2023-07-14","cited_by_count":1,"area":"agents"},{"id":"2311.09109","title":"Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2312.07868","title":"Graph vs. Sequence: An Empirical Study on Knowledge Forms for Knowledge-Grounded Dialogue","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2402.02077","title":"Investigating Content Planning for Navigating Trade-offs in Knowledge-Grounded Dialogue","created":"2024-02-03","cited_by_count":1,"area":null},{"id":"2409.16658","title":"Pre-trained Language Models Return Distinguishable Probability Distributions to Unfaithfully Hallucinated Texts","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.18114","title":"Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2504.10167","title":"C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2505.15633","title":"Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate Questions","created":"2025-05-21","cited_by_count":1,"area":"rag"},{"id":"2506.23026","title":"Machine Assistant with Reliable Knowledge: Enhancing Student Learning via RAG-based Retrieval","created":"2025-06-28","cited_by_count":1,"area":"rag"},{"id":"2508.19272","title":"RAGAPHENE: A RAG Annotation Platform with Human Enhancements and Edits","created":"2025-08-22","cited_by_count":1,"area":"rag"},{"id":"2510.19318","title":"HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2510.27052","title":"VISTA: Verification In Sequential Turn-based Assessment","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2605.07677","title":"TRACE: Tourism Recommendation with Accountable Citation Evidence","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.29523","title":"K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance","created":"2026-05-28","cited_by_count":1,"area":"rag"},{"id":"2606.11127","title":"Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation","created":"2026-06-09","cited_by_count":1,"area":"alignment"},{"id":"2606.31435","title":"CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.22661","title":"TRE: Training-Free Hallucination Detection for Diffusion Language Models","created":"2026-06-29","cited_by_count":1,"area":"diffusion"},{"id":"2608.28930","title":"The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2405.15110","title":"CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2406.09702","title":"Detecting Response Generation Not Requiring Factual Judgment","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2410.03839","title":"FaithCAMERA: Construction of a Faithful Dataset for Ad Text Generation","created":"2024-10-04","cited_by_count":0,"area":null},{"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":"2509.20097","title":"Integrated Framework for LLM Evaluation with Answer Generation","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.11897","title":"A Longitudinal Study on Different Annotator Feedback Loops in Complex RAG Tasks","created":"2025-10-13","cited_by_count":0,"area":"rag"},{"id":"2602.11165","title":"Assessing LLM Reliability on Temporally Recent Open-Domain Questions","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2603.10524","title":"AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations","created":"2026-03-11","cited_by_count":0,"area":"rag"},{"id":"2604.09034","title":"The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.05810","title":"CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2605.21949","title":"Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation","created":"2026-05-21","cited_by_count":0,"area":"rag"},{"id":"2606.05170","title":"ERRORQUAKE: Heavy-Tailed Error Severity Distributions in Open-Weight Large Language Models","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2607.09349","title":"Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation","created":"2026-07-10","cited_by_count":0,"area":"rag"}],"next_cursor":"100"}