{"total":132,"rows":[{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"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":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2305.16739","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","created":"2023-05-26","cited_by_count":288,"area":null},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287,"area":null},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256,"area":null},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244,"area":null},{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234,"area":null},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232,"area":null},{"id":"2305.13281","title":"LM vs LM: Detecting Factual Errors via Cross Examination","created":"2023-05-22","cited_by_count":156,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"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":"2303.01432","title":"WiCE: Real-World Entailment for Claims in Wikipedia","created":"2023-03-02","cited_by_count":120,"area":null},{"id":"2204.10757","title":"FaithDial: A Faithful Benchmark for Information-Seeking Dialogue","created":"2022-04-22","cited_by_count":109,"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":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2311.09766","title":"LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores","created":"2023-11-16","cited_by_count":90,"area":null},{"id":"2305.11171","title":"TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models","created":"2023-05-18","cited_by_count":83,"area":null},{"id":"2303.07274","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","created":"2023-03-13","cited_by_count":80,"area":null},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77,"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":"2308.11696","title":"Efficient Benchmarking of Language Models","created":"2023-08-22","cited_by_count":71,"area":null},{"id":"2202.07654","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","created":"2022-02-15","cited_by_count":67,"area":null},{"id":"2305.14292","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","created":"2023-05-23","cited_by_count":67,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2110.08222","title":"DialFact: A Benchmark for Fact-Checking in Dialogue","created":"2021-10-15","cited_by_count":62,"area":null},{"id":"2210.12563","title":"On the Limitations of Reference-Free Evaluations of Generated Text","created":"2022-10-22","cited_by_count":52,"area":null},{"id":"2204.07447","title":"Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters","created":"2022-04-15","cited_by_count":44,"area":null},{"id":"2207.00397","title":"Conditional Generation with a Question-Answering Blueprint","created":"2022-07-01","cited_by_count":44,"area":null},{"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":"2212.10622","title":"mFACE: Multilingual Summarization with Factual Consistency Evaluation","created":"2022-12-20","cited_by_count":42,"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":"2301.09919","title":"Opportunities and Challenges in Neural Dialog Tutoring","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2401.14367","title":"Genie: Achieving Human Parity in Content-Grounded Datasets Generation","created":"2024-01-25","cited_by_count":31,"area":null},{"id":"2401.14493","title":"K-QA: A Real-World Medical Q&A Benchmark","created":"2024-01-25","cited_by_count":31,"area":null},{"id":"2402.10412","title":"Measuring and Reducing LLM Hallucination without Gold-Standard Answers","created":"2024-02-16","cited_by_count":31,"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":"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":"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":"2404.02935","title":"KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking","created":"2024-04-03","cited_by_count":26,"area":"lr"},{"id":"2412.06676","title":"I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token","created":"2024-12-09","cited_by_count":26,"area":null},{"id":"2403.03307","title":"Book2Dial: Generating Teacher-Student Interactions from Textbooks for Cost-Effective Development of Educational Chatbots","created":"2024-03-05","cited_by_count":25,"area":"distill"},{"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":"2401.08574","title":"Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability","created":"2024-01-16","cited_by_count":22,"area":null},{"id":"2410.18889","title":"Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance","created":"2024-10-24","cited_by_count":20,"area":null},{"id":"2310.08372","title":"Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment","created":"2023-10-12","cited_by_count":19,"area":null},{"id":"2208.01030","title":"SMART: Sentences as Basic Units for Text Evaluation","created":"2022-08-01","cited_by_count":18,"area":null},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2406.17260","title":"Mitigating Hallucination in Fictional Character Role-Play","created":"2024-06-25","cited_by_count":18,"area":null},{"id":"2302.05852","title":"\"Why is this misleading?\": Detecting News Headline Hallucinations with Explanations","created":"2023-02-12","cited_by_count":17,"area":null},{"id":"2406.15264","title":"Towards Fine-Grained Citation Evaluation in Generated Text: A Comparative Analysis of Faithfulness Metrics","created":"2024-06-21","cited_by_count":17,"area":"rag"},{"id":"2408.03573","title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling","created":"2024-08-07","cited_by_count":17,"area":null},{"id":"2409.02976","title":"Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Models","created":"2024-09-04","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":"2410.07473","title":"Localizing Factual Inconsistencies in Attributable Text Generation","created":"2024-10-09","cited_by_count":14,"area":null},{"id":"2305.16819","title":"With a Little Push, NLI Models can Robustly and Efficiently Predict Faithfulness","created":"2023-05-26","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":"2301.09008","title":"Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference","created":"2023-01-21","cited_by_count":11,"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":"2210.13449","title":"Controlled Text Reduction","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2407.19474","title":"Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models","created":"2024-07-28","cited_by_count":10,"area":null},{"id":"2504.07583","title":"Do LLMs Understand Your Translations? Evaluating Paragraph-level MT with Question Answering","created":"2025-04-10","cited_by_count":10,"area":null},{"id":"2209.05401","title":"MaXM: Towards Multilingual Visual Question Answering","created":"2022-09-12","cited_by_count":9,"area":null},{"id":"2211.12130","title":"Converge to the Truth: Factual Error Correction via Iterative Constrained Editing","created":"2022-11-22","cited_by_count":9,"area":null},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2205.12416","title":"Counterfactual Data Augmentation improves Factuality of Abstractive Summarization","created":"2022-05-25","cited_by_count":8,"area":null},{"id":"2305.07355","title":"ZARA: Improving Few-Shot Self-Rationalization for Small Language Models","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2310.14981","title":"Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2406.04625","title":"Key-Element-Informed sLLM Tuning for Document Summarization","created":"2024-06-07","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":"2310.16964","title":"Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2404.07060","title":"Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study","created":"2024-04-10","cited_by_count":7,"area":"rag"},{"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":"2207.00630","title":"QA Is the New KR: Question-Answer Pairs as Knowledge Bases","created":"2022-07-01","cited_by_count":6,"area":null},{"id":"2212.10057","title":"WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2304.14318","title":"q2d: Turning Questions into Dialogs to Teach Models How to Search","created":"2023-04-27","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":"2407.05474","title":"Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses","created":"2024-07-07","cited_by_count":5,"area":"synth"},{"id":"2408.10490","title":"Analysis of Plan-based Retrieval for Grounded Text Generation","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2411.09018","title":"Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions","created":"2024-11-13","cited_by_count":5,"area":"mllm"},{"id":"2304.07101","title":"Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10","created":"2023-04-14","cited_by_count":4,"area":null},{"id":"2305.15026","title":"Transferring Visual Attributes from Natural Language to Verified Image Generation","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2305.17819","title":"Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation","created":"2023-05-28","cited_by_count":4,"area":null},{"id":"2308.15851","title":"Prompting Vision Language Model with Knowledge from Large Language Model for Knowledge-Based VQA","created":"2023-08-30","cited_by_count":4,"area":"mllm"},{"id":"2310.00598","title":"A Novel Computational and Modeling Foundation for Automatic Coherence Assessment","created":"2023-10-01","cited_by_count":4,"area":null},{"id":"2310.08764","title":"Calibrating Likelihoods towards Consistency in Summarization Models","created":"2023-10-12","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":"2404.03344","title":"Schroedinger's Threshold: When the AUC doesn't predict Accuracy","created":"2024-04-04","cited_by_count":4,"area":null},{"id":"2108.10763","title":"ComSum: Commit Messages Summarization and Meaning Preservation","created":"2021-08-23","cited_by_count":3,"area":null},{"id":"2210.08859","title":"Social Biases in Automatic Evaluation Metrics for NLG","created":"2022-10-17","cited_by_count":3,"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":"2212.03747","title":"Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2212.09682","title":"Multilingual Sequence-to-Sequence Models for Hebrew NLP","created":"2022-12-19","cited_by_count":3,"area":null},{"id":"2401.09248","title":"Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues","created":"2024-01-17","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"}],"next_cursor":"100"}