{"total":256,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459,"area":"lr"},{"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":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282,"area":null},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595,"area":null},{"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":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324,"area":null},{"id":"2304.09848","title":"Evaluating Verifiability in Generative Search Engines","created":"2023-04-19","cited_by_count":303,"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":"2311.09476","title":"ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems","created":"2023-11-16","cited_by_count":265,"area":"rag"},{"id":"2406.19314","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","created":"2024-06-27","cited_by_count":262,"area":null},{"id":"2505.04588","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","created":"2025-05-07","cited_by_count":208,"area":null},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"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":"2204.07931","title":"On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?","created":"2022-04-17","cited_by_count":138,"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":"2407.11005","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","created":"2024-06-25","cited_by_count":117,"area":"rag"},{"id":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112,"area":null},{"id":"2305.06984","title":"Evaluating Open-Domain Question Answering in the Era of Large Language Models","created":"2023-05-11","cited_by_count":111,"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":"2409.00729","title":"ContextCite: Attributing Model Generation to Context","created":"2024-09-01","cited_by_count":98,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2211.05655","title":"DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering","created":"2022-11-10","cited_by_count":96,"area":null},{"id":"2301.13298","title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","created":"2023-01-30","cited_by_count":96,"area":null},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91,"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":"2305.06311","title":"Automatic Evaluation of Attribution by Large Language Models","created":"2023-05-10","cited_by_count":72,"area":null},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2411.06037","title":"Sufficient Context: A New Lens on Retrieval Augmented Generation Systems","created":"2024-11-09","cited_by_count":72,"area":"rag"},{"id":"2311.03731","title":"A Survey of Large Language Models Attribution","created":"2023-11-07","cited_by_count":71,"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":"2402.00559","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","created":"2024-02-01","cited_by_count":65,"area":"lr"},{"id":"2209.14290","title":"FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation","created":"2022-09-28","cited_by_count":63,"area":"rag"},{"id":"2407.08488","title":"Lynx: An Open Source Hallucination Evaluation Model","created":"2024-07-11","cited_by_count":57,"area":"rag"},{"id":"2307.16883","title":"HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution","created":"2023-07-31","cited_by_count":56,"area":null},{"id":"2403.17104","title":"Attribute First, then Generate: Locally-attributable Grounded Text Generation","created":"2024-03-25","cited_by_count":54,"area":null},{"id":"2509.07968","title":"SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge","created":"2025-09-09","cited_by_count":54,"area":null},{"id":"2305.14908","title":"PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions","created":"2023-05-24","cited_by_count":53,"area":null},{"id":"2306.00024","title":"Self-Verification Improves Few-Shot Clinical Information Extraction","created":"2023-05-30","cited_by_count":52,"area":"lr"},{"id":"2311.07838","title":"LLatrieval: LLM-Verified Retrieval for Verifiable Generation","created":"2023-11-14","cited_by_count":52,"area":null},{"id":"2501.03200","title":"The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input","created":"2025-01-06","cited_by_count":52,"area":null},{"id":"2401.17043","title":"CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models","created":"2024-01-30","cited_by_count":50,"area":"rag"},{"id":"2601.20975","title":"DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents","created":"2026-01-28","cited_by_count":50,"area":"agents"},{"id":"2310.12150","title":"Understanding Retrieval Augmentation for Long-Form Question Answering","created":"2023-10-18","cited_by_count":45,"area":null},{"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":"2406.20079","title":"Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification","created":"2024-06-28","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":"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":"2305.13252","title":"\"According to ...\": Prompting Language Models Improves Quoting from Pre-Training Data","created":"2023-05-22","cited_by_count":42,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"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":"2409.11242","title":"Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse","created":"2024-09-17","cited_by_count":34,"area":"rag"},{"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":"2305.11694","title":"QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set Operations","created":"2023-05-19","cited_by_count":31,"area":null},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2404.01019","title":"Source-Aware Training Enables Knowledge Attribution in Language Models","created":"2024-04-01","cited_by_count":30,"area":null},{"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":"2404.03381","title":"Learning to Plan and Generate Text with Citations","created":"2024-04-04","cited_by_count":28,"area":null},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27,"area":null},{"id":"2404.16032","title":"Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents","created":"2024-04-24","cited_by_count":27,"area":"rag"},{"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":"2402.15089","title":"AttributionBench: How Hard is Automatic Attribution Evaluation?","created":"2024-02-23","cited_by_count":26,"area":null},{"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":"2503.05683","title":"WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs","created":"2025-03-07","cited_by_count":26,"area":null},{"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":"2406.13663","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":25,"area":"rag"},{"id":"2506.08500","title":"DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs","created":"2025-06-10","cited_by_count":25,"area":"rag"},{"id":"2310.05634","title":"Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution","created":"2023-10-09","cited_by_count":24,"area":null},{"id":"2310.02932","title":"Assessing Large Language Models on Climate Information","created":"2023-10-04","cited_by_count":23,"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":"2405.00982","title":"On the Evaluation of Machine-Generated Reports","created":"2024-05-02","cited_by_count":23,"area":null},{"id":"2305.14332","title":"Evaluating and Modeling Attribution for Cross-Lingual Question Answering","created":"2023-05-23","cited_by_count":21,"area":null},{"id":"2312.09075","title":"Towards Verifiable Text Generation with Evolving Memory and Self-Reflection","created":"2023-12-14","cited_by_count":21,"area":null},{"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":"2307.02185","title":"Citation: A Key to Building Responsible and Accountable Large Language Models","created":"2023-07-05","cited_by_count":20,"area":null},{"id":"2307.03067","title":"DeepOnto: A Python Package for Ontology Engineering with Deep Learning","created":"2023-07-06","cited_by_count":20,"area":null},{"id":"2311.04335","title":"Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations","created":"2023-11-07","cited_by_count":20,"area":null},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2311.04886","title":"SEMQA: Semi-Extractive Multi-Source Question Answering","created":"2023-11-08","cited_by_count":19,"area":null},{"id":"2502.10855","title":"Towards Effective Extraction and Evaluation of Factual Claims","created":"2025-02-15","cited_by_count":19,"area":null},{"id":"2312.10868","title":"From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape","created":"2023-12-18","cited_by_count":18,"area":"moe"},{"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":"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":"2512.10791","title":"The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality","created":"2025-12-11","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":"2503.18174","title":"GINGER: Grounded Information Nugget-Based Generation of Responses","created":"2025-03-23","cited_by_count":16,"area":"rag"},{"id":"2603.19469","title":"A Framework for Formalizing LLM Agent Security","created":"2026-03-19","cited_by_count":16,"area":"agents"},{"id":"2302.13793","title":"Dr ChatGPT, tell me what I want to hear: How prompt knowledge impacts health answer correctness","created":"2023-02-23","cited_by_count":15,"area":null},{"id":"2402.12368","title":"A synthetic data approach for domain generalization of NLI models","created":"2024-02-19","cited_by_count":15,"area":"synth"},{"id":"2406.06125","title":"Verifiable Generation with Subsentence-Level Fine-Grained Citations","created":"2024-06-10","cited_by_count":15,"area":null},{"id":"2409.11598","title":"Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation","created":"2024-09-17","cited_by_count":15,"area":"rag"},{"id":"2309.09401","title":"ChatGPT Hallucinates when Attributing Answers","created":"2023-09-17","cited_by_count":14,"area":null}],"next_cursor":"100"}