{"total":104,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327,"area":null},{"id":"2404.10774","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","created":"2024-04-16","cited_by_count":257,"area":"rag"},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2212.07981","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","created":"2022-12-15","cited_by_count":142,"area":null},{"id":"2305.10400","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","created":"2023-05-17","cited_by_count":108,"area":"mllm"},{"id":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"area":null},{"id":"2311.08596","title":"Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment","created":"2023-11-14","cited_by_count":77,"area":null},{"id":"2310.00741","title":"FELM: Benchmarking Factuality Evaluation of Large Language Models","created":"2023-10-01","cited_by_count":66,"area":null},{"id":"2402.13249","title":"TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization","created":"2024-02-20","cited_by_count":66,"area":null},{"id":"2305.08281","title":"FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge","created":"2023-05-14","cited_by_count":55,"area":null},{"id":"2403.00553","title":"Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores","created":"2024-03-01","cited_by_count":50,"area":null},{"id":"2312.10160","title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","created":"2023-12-15","cited_by_count":49,"area":"mllm"},{"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":"2211.15914","title":"Prompted Opinion Summarization with GPT-3.5","created":"2022-11-29","cited_by_count":44,"area":null},{"id":"2212.10622","title":"mFACE: Multilingual Summarization with Factual Consistency Evaluation","created":"2022-12-20","cited_by_count":42,"area":null},{"id":"2212.09968","title":"On Improving Summarization Factual Consistency from Natural Language Feedback","created":"2022-12-20","cited_by_count":38,"area":"alignment"},{"id":"2305.14540","title":"LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond","created":"2023-05-23","cited_by_count":38,"area":"lr"},{"id":"2403.02270","title":"FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction","created":"2024-03-04","cited_by_count":28,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2406.03487","title":"Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends","created":"2024-06-05","cited_by_count":25,"area":null},{"id":"2311.00681","title":"Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs","created":"2023-11-01","cited_by_count":24,"area":null},{"id":"2410.13210","title":"FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs","created":"2024-10-17","cited_by_count":24,"area":"rag"},{"id":"2402.17630","title":"Fine-Grained Natural Language Inference Based Faithfulness Evaluation for Diverse Summarisation Tasks","created":"2024-02-27","cited_by_count":23,"area":null},{"id":"2410.23609","title":"On Positional Bias of Faithfulness for Long-form Summarization","created":"2024-10-31","cited_by_count":22,"area":null},{"id":"2505.04847","title":"Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards","created":"2025-05-07","cited_by_count":20,"area":"rag"},{"id":"2403.01061","title":"Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers","created":"2024-03-02","cited_by_count":19,"area":null},{"id":"2402.11456","title":"FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidence","created":"2024-02-18","cited_by_count":18,"area":null},{"id":"2410.13961","title":"From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization","created":"2024-10-17","cited_by_count":17,"area":null},{"id":"2311.09335","title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization","created":"2023-11-15","cited_by_count":16,"area":null},{"id":"2503.18174","title":"GINGER: Grounded Information Nugget-Based Generation of Responses","created":"2025-03-23","cited_by_count":16,"area":"rag"},{"id":"2404.11184","title":"FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2306.16931","title":"UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?","created":"2023-06-29","cited_by_count":14,"area":null},{"id":"2410.07473","title":"Localizing Factual Inconsistencies in Attributable Text Generation","created":"2024-10-09","cited_by_count":14,"area":null},{"id":"2501.17144","title":"FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data","created":"2025-01-28","cited_by_count":14,"area":null},{"id":"2506.13342","title":"Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers","created":"2025-06-16","cited_by_count":13,"area":null},{"id":"2210.04829","title":"Hierarchical3D Adapters for Long Video-to-text Summarization","created":"2022-10-10","cited_by_count":12,"area":null},{"id":"2210.11777","title":"Analyzing and Evaluating Faithfulness in Dialogue Summarization","created":"2022-10-21","cited_by_count":12,"area":null},{"id":"2502.16514","title":"GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking","created":"2025-02-23","cited_by_count":12,"area":null},{"id":"2311.09521","title":"AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation","created":"2023-11-16","cited_by_count":11,"area":null},{"id":"2411.16638","title":"Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2506.00549","title":"Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages","created":"2025-05-31","cited_by_count":11,"area":null},{"id":"2212.02712","title":"Improved Beam Search for Hallucination Mitigation in Abstractive Summarization","created":"2022-12-06","cited_by_count":10,"area":null},{"id":"2305.14069","title":"Evaluating Factual Consistency of Summaries with Large Language Models","created":"2023-05-23","cited_by_count":10,"area":null},{"id":"2305.16548","title":"Annotating and Detecting Fine-grained Factual Errors for Dialogue Summarization","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2402.03509","title":"Evaluating the Factuality of Zero-shot Summarizers Across Varied Domains","created":"2024-02-05","cited_by_count":10,"area":null},{"id":"2407.01080","title":"Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinese","created":"2024-07-01","cited_by_count":10,"area":"rag"},{"id":"2502.08514","title":"Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation","created":"2025-02-12","cited_by_count":10,"area":"agents"},{"id":"2407.06501","title":"STORYSUMM: Evaluating Faithfulness in Story Summarization","created":"2024-07-09","cited_by_count":9,"area":null},{"id":"2503.15272","title":"MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration","created":"2025-03-19","cited_by_count":9,"area":"agents"},{"id":"2411.19655","title":"Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2501.07482","title":"TiEBe: Tracking Language Model Recall of Notable Worldwide Events Through Time","created":"2025-01-13","cited_by_count":8,"area":null},{"id":"2212.09955","title":"BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics","created":"2022-12-20","cited_by_count":7,"area":null},{"id":"2305.14981","title":"Improving Factuality of Abstractive Summarization without Sacrificing Summary Quality","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2310.05857","title":"Improving Summarization with Human Edits","created":"2023-10-09","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":"2512.08892","title":"Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders","created":"2025-12-09","cited_by_count":7,"area":"rag"},{"id":"2305.14548","title":"Interpretable Automatic Fine-grained Inconsistency Detection in Text Summarization","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2505.12348","title":"Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification","created":"2025-05-18","cited_by_count":6,"area":"lr"},{"id":"2505.15291","title":"Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2402.12821","title":"Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy","created":"2024-02-20","cited_by_count":5,"area":null},{"id":"2409.15090","title":"Using Similarity to Evaluate Factual Consistency in Summaries","created":"2024-09-23","cited_by_count":5,"area":null},{"id":"2310.08764","title":"Calibrating Likelihoods towards Consistency in Summarization Models","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2311.09741","title":"P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models","created":"2023-11-16","cited_by_count":4,"area":"diffusion"},{"id":"2412.10689","title":"Learning to Verify Summary Facts with Fine-Grained LLM Feedback","created":"2024-12-14","cited_by_count":4,"area":"alignment"},{"id":"2505.15792","title":"Long-Form Information Alignment Evaluation Beyond Atomic Facts","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2309.08873","title":"X-PARADE: Cross-Lingual Textual Entailment and Information Divergence across Paragraphs","created":"2023-09-16","cited_by_count":3,"area":null},{"id":"2401.11452","title":"Towards Reliable and Factual Response Generation: Detecting Unanswerable Questions in Information-Seeking Conversations","created":"2024-01-21","cited_by_count":3,"area":null},{"id":"2506.19607","title":"Correcting Hallucinations in News Summaries: Exploration of Self-Correcting LLM Methods with External Knowledge","created":"2025-06-24","cited_by_count":3,"area":null},{"id":"2512.20182","title":"FaithLens: Detecting and Explaining Faithfulness Hallucination","created":"2025-12-23","cited_by_count":3,"area":"rag"},{"id":"2306.11256","title":"GUMSum: Multi-Genre Data and Evaluation for English Abstractive Summarization","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2403.05788","title":"On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization","created":"2024-03-09","cited_by_count":2,"area":null},{"id":"2404.13246","title":"ISQA: Informative Factuality Feedback for Scientific Summarization","created":"2024-04-20","cited_by_count":2,"area":null},{"id":"2406.13009","title":"Detecting Errors through Ensembling Prompts (DEEP): An End-to-End LLM Framework for Detecting Factual Errors","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2409.19507","title":"A Critical Look at Meta-evaluating Summarisation Evaluation Metrics","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2410.03461","title":"Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation","created":"2024-10-04","cited_by_count":2,"area":"rag"},{"id":"2507.11981","title":"Simplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2402.14488","title":"Does the Generator Mind its Contexts? An Analysis of Generative Model Faithfulness under Context Transfer","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2402.14854","title":"A Dual-Prompting for Interpretable Mental Health Language Models","created":"2024-02-20","cited_by_count":1,"area":"mechinterp"},{"id":"2405.11487","title":"\"Previously on ...\" From Recaps to Story Summarization","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2408.15171","title":"Measuring text summarization factuality using atomic facts entailment metrics in the context of retrieval augmented generation","created":"2024-08-27","cited_by_count":1,"area":"rag"},{"id":"2410.13037","title":"LFOSum: Summarizing Long-form Opinions with Large Language Models","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2412.13378","title":"SummExecEdit: A Factual Consistency Benchmark in Summarization with Executable Edits","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2509.22582","title":"Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2608.03372","title":"FACTWASH: Catching AI Rewrites That Wash Hearsay into Fact","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2312.06022","title":"Exploiting Representation Bias for Data Distillation in Abstractive Text Summarization","created":"2023-12-10","cited_by_count":0,"area":null},{"id":"2402.08581","title":"Improving Factual Error Correction for Abstractive Summarization via Data Distillation and Conditional-generation Cloze","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2408.04114","title":"Zero-shot Factual Consistency Evaluation Across Domains","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2510.05769","title":"InforME: Improving Informativeness of Abstractive Text Summarization With Informative Attention Guided by Named Entity Salience","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2512.03634","title":"AlignCheck: a Semantic Open-Domain Metric for Factual Consistency Assessment","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2602.08149","title":"DIAL-SUMMER: A Structured Evaluation Framework of Hierarchical Errors in Dialogue Summaries","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2604.01652","title":"ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.01657","title":"What Do Claim Verification Datasets Actually Test? A Reasoning Trace Analysis","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2605.26840","title":"Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2605.29712","title":"Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies","created":"2026-05-28","cited_by_count":0,"area":"rag"},{"id":"2606.13216","title":"Layer-Resolved Optimal Transport for Hallucination Detection in NMT and Abstractive Summarization","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.17524","title":"Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.00205","title":"Averaging Bias: Human Faithfulness Annotations are not Locally Faithful","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.06953","title":"Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":"100"}