{"total":119,"rows":[{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975,"area":null},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802,"area":null},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692,"area":null},{"id":"2103.08541","title":"Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence","created":"2021-03-15","cited_by_count":225,"area":null},{"id":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167,"area":null},{"id":"2104.08704","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","created":"2021-04-18","cited_by_count":138,"area":null},{"id":"2109.09784","title":"Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization","created":"2021-08-30","cited_by_count":129,"area":null},{"id":"2305.15852","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","created":"2023-05-25","cited_by_count":124,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2212.14882","title":"ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports","created":"2022-12-30","cited_by_count":101,"area":null},{"id":"2311.01740","title":"SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency","created":"2023-11-03","cited_by_count":90,"area":null},{"id":"2403.06448","title":"Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models","created":"2024-03-11","cited_by_count":86,"area":null},{"id":"2104.14839","title":"The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey","created":"2021-04-30","cited_by_count":79,"area":null},{"id":"2212.08597","title":"Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better","created":"2022-12-16","cited_by_count":75,"area":null},{"id":"2210.13210","title":"Mutual Information Alleviates Hallucinations in Abstractive Summarization","created":"2022-10-24","cited_by_count":68,"area":null},{"id":"2208.05309","title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","created":"2022-08-10","cited_by_count":61,"area":null},{"id":"2109.06379","title":"Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation","created":"2021-09-14","cited_by_count":60,"area":null},{"id":"2108.13684","title":"Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization","created":"2021-08-31","cited_by_count":51,"area":null},{"id":"2307.04408","title":"TIM: Teaching Large Language Models to Translate with Comparison","created":"2023-07-10","cited_by_count":50,"area":null},{"id":"2301.07779","title":"Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection","created":"2023-01-18","cited_by_count":44,"area":null},{"id":"2305.04118","title":"Exploring Human-Like Translation Strategy with Large Language Models","created":"2023-05-06","cited_by_count":44,"area":null},{"id":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44,"area":null},{"id":"2312.05200","title":"DelucionQA: Detecting Hallucinations in Domain-specific Question Answering","created":"2023-12-08","cited_by_count":43,"area":null},{"id":"2305.13194","title":"SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation","created":"2023-05-22","cited_by_count":42,"area":null},{"id":"2305.11746","title":"HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation","created":"2023-05-19","cited_by_count":35,"area":null},{"id":"2310.03951","title":"Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations","created":"2023-10-06","cited_by_count":35,"area":null},{"id":"2112.11941","title":"CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models","created":"2021-12-22","cited_by_count":34,"area":null},{"id":"2401.06796","title":"AI Hallucinations: A Misnomer Worth Clarifying","created":"2024-01-09","cited_by_count":34,"area":null},{"id":"2402.12052","title":"Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs","created":"2024-02-19","cited_by_count":34,"area":null},{"id":"2310.03368","title":"Evaluating Hallucinations in Chinese Large Language Models","created":"2023-10-05","cited_by_count":33,"area":null},{"id":"2410.22685","title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","created":"2024-10-30","cited_by_count":30,"area":null},{"id":"2110.05456","title":"Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation","created":"2021-10-11","cited_by_count":29,"area":null},{"id":"2204.10290","title":"Learning to Revise References for Faithful Summarization","created":"2022-04-13","cited_by_count":28,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2403.04307","title":"HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild","created":"2024-03-07","cited_by_count":27,"area":null},{"id":"2404.09889","title":"Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval","created":"2024-04-15","cited_by_count":27,"area":null},{"id":"2504.11975","title":"SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes","created":"2025-04-16","cited_by_count":27,"area":null},{"id":"2210.12814","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","created":"2022-10-23","cited_by_count":26,"area":null},{"id":"2403.07726","title":"SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes","created":"2024-03-12","cited_by_count":24,"area":null},{"id":"2206.01843","title":"Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning","created":"2022-06-03","cited_by_count":21,"area":null},{"id":"2401.08358","title":"Hallucination Detection and Hallucination Mitigation: An Investigation","created":"2024-01-16","cited_by_count":21,"area":null},{"id":"2504.18243","title":"DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering","created":"2025-04-25","cited_by_count":20,"area":null},{"id":"2309.02654","title":"Zero-Resource Hallucination Prevention for Large Language Models","created":"2023-09-06","cited_by_count":19,"area":null},{"id":"2212.10179","title":"Toward Human-Like Evaluation for Natural Language Generation with Error Analysis","created":"2022-12-20","cited_by_count":18,"area":null},{"id":"2308.14391","title":"FIRE: Food Image to REcipe generation","created":"2023-08-28","cited_by_count":18,"area":null},{"id":"2404.05411","title":"Know When To Stop: A Study of Semantic Drift in Text Generation","created":"2024-04-08","cited_by_count":18,"area":null},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2112.07381","title":"You Only Need One Model for Open-domain Question Answering","created":"2021-12-14","cited_by_count":17,"area":null},{"id":"2307.04761","title":"Understanding Counterspeech for Online Harm Mitigation","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2407.09417","title":"Mitigating Entity-Level Hallucination in Large Language Models","created":"2024-07-12","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":"2110.06393","title":"Attention-guided Generative Models for Extractive Question Answering","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2305.14221","title":"Question Answering as Programming for Solving Time-Sensitive Questions","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2407.01942","title":"Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2407.06071","title":"From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty","created":"2024-07-08","cited_by_count":14,"area":null},{"id":"2211.06196","title":"Improving Factual Consistency in Summarization with Compression-Based Post-Editing","created":"2022-11-11","cited_by_count":13,"area":null},{"id":"2212.09631","title":"Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation","created":"2022-12-19","cited_by_count":13,"area":null},{"id":"2110.07166","title":"CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization","created":"2021-10-14","cited_by_count":11,"area":null},{"id":"2203.01927","title":"As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning","created":"2022-03-03","cited_by_count":11,"area":null},{"id":"2305.07021","title":"Simple Token-Level Confidence Improves Caption Correctness","created":"2023-05-11","cited_by_count":11,"area":null},{"id":"2406.07735","title":"REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2410.02899","title":"FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2106.02278","title":"AgreeSum: Agreement-Oriented Multi-Document Summarization","created":"2021-06-04","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":"2311.02851","title":"Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding","created":"2023-11-06","cited_by_count":10,"area":null},{"id":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2305.07615","title":"What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific Summarization","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2411.04847","title":"Prompt-Guided Internal States for Hallucination Detection of Large Language Models","created":"2024-11-07","cited_by_count":8,"area":null},{"id":"2104.00336","title":"Mitigating Media Bias through Neutral Article Generation","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2204.05879","title":"Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies","created":"2022-04-12","cited_by_count":7,"area":null},{"id":"2310.15319","title":"Hallucination Detection for Grounded Instruction Generation","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2211.12118","title":"HaRiM$^+$: Evaluating Summary Quality with Hallucination Risk","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2212.10012","title":"Language Modeling with Latent Situations","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2309.11669","title":"Construction of Paired Knowledge Graph-Text Datasets Informed by Cyclic Evaluation","created":"2023-09-20","cited_by_count":6,"area":null},{"id":"2402.15422","title":"A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models","created":"2024-02-23","cited_by_count":6,"area":null},{"id":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","cited_by_count":6,"area":null},{"id":"2404.09480","title":"Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information","created":"2024-04-15","cited_by_count":6,"area":null},{"id":"2509.15350","title":"Real, Fake, or Manipulated? Detecting Machine-Influenced Text","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2305.10928","title":"Multilingual Event Extraction from Historical Newspaper Adverts","created":"2023-05-18","cited_by_count":5,"area":null},{"id":"2307.00963","title":"Challenges in Domain-Specific Abstractive Summarization and How to Overcome them","created":"2023-07-03","cited_by_count":5,"area":null},{"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":"2402.01769","title":"Redefining \"Hallucination\" in LLMs: Towards a psychology-informed framework for mitigating misinformation","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2405.10630","title":"Medical Dialogue: A Survey of Categories, Methods, Evaluation and Challenges","created":"2024-05-17","cited_by_count":5,"area":null},{"id":"2205.14748","title":"Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition","created":"2022-05-29","cited_by_count":4,"area":null},{"id":"2212.01611","title":"CoP: Factual Inconsistency Detection by Controlling the Preference","created":"2022-12-03","cited_by_count":4,"area":null},{"id":"2302.08975","title":"Towards Fine-Grained Information: Identifying the Type and Location of Translation Errors","created":"2023-02-17","cited_by_count":4,"area":null},{"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":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","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":"2411.08254","title":"Toward Automated Validation of Language Model Synthesized Test Cases using Semantic Entropy","created":"2024-11-13","cited_by_count":4,"area":null},{"id":"2109.07343","title":"Mi{\\dh}eind's WMT 2021 submission","created":"2021-09-15","cited_by_count":3,"area":null},{"id":"2111.06787","title":"BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation","created":"2021-11-12","cited_by_count":3,"area":null},{"id":"2305.09154","title":"Progressive Translation: Improving Domain Robustness of Neural Machine Translation with Intermediate Sequences","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2404.03491","title":"A Cause-Effect Look at Alleviating Hallucination of Knowledge-grounded Dialogue Generation","created":"2024-04-04","cited_by_count":3,"area":null},{"id":"2104.08724","title":"Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation","created":"2021-04-18","cited_by_count":2,"area":null},{"id":"2402.16973","title":"Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections","created":"2024-02-26","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}],"next_cursor":"100"}