{"total":54,"rows":[{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017,"area":"lr"},{"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":"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":"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":"2309.01809","title":"Are Emergent Abilities in Large Language Models just In-Context Learning?","created":"2023-09-04","cited_by_count":109,"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":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73,"area":null},{"id":"2310.07064","title":"Large Language Models can Learn Rules","created":"2023-10-10","cited_by_count":69,"area":null},{"id":"2509.18970","title":"LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions","created":"2025-09-23","cited_by_count":50,"area":"agents"},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2308.07922","title":"RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models","created":"2023-08-15","cited_by_count":37,"area":"rag"},{"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":"2310.03368","title":"Evaluating Hallucinations in Chinese Large Language Models","created":"2023-10-05","cited_by_count":33,"area":null},{"id":"2406.00936","title":"A Survey of Useful LLM Evaluation","created":"2024-06-03","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":"2310.02409","title":"Dodo: Dynamic Contextual Compression for Decoder-only LMs","created":"2023-10-03","cited_by_count":23,"area":null},{"id":"2402.17896","title":"Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents","created":"2024-02-27","cited_by_count":23,"area":"agents"},{"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":"2406.03075","title":"Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework","created":"2024-06-05","cited_by_count":19,"area":"agents"},{"id":"2408.12325","title":"Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2308.00245","title":"The Hitchhiker's Guide to Program Analysis: A Journey with Large Language Models","created":"2023-08-01","cited_by_count":18,"area":null},{"id":"2503.12600","title":"GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation","created":"2025-03-16","cited_by_count":17,"area":null},{"id":"2405.06545","title":"Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval","created":"2024-05-10","cited_by_count":16,"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":"2309.05217","title":"Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis","created":"2023-09-11","cited_by_count":15,"area":null},{"id":"2408.08978","title":"See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses","created":"2024-08-16","cited_by_count":15,"area":null},{"id":"2403.10882","title":"Optimizing Language Augmentation for Multilingual Large Language Models: A Case Study on Korean","created":"2024-03-16","cited_by_count":14,"area":null},{"id":"2407.21443","title":"Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency","created":"2024-07-31","cited_by_count":14,"area":"lr"},{"id":"2412.20545","title":"The Impact of Prompt Programming on Function-Level Code Generation","created":"2024-12-29","cited_by_count":13,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2408.05093","title":"Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models","created":"2024-08-09","cited_by_count":12,"area":"lr"},{"id":"2310.08773","title":"Examining the Potential and Pitfalls of ChatGPT in Science and Engineering Problem-Solving","created":"2023-10-12","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":"2310.00259","title":"AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models","created":"2023-09-30","cited_by_count":10,"area":null},{"id":"2312.02206","title":"Axiomatic Preference Modeling for Longform Question Answering","created":"2023-12-02","cited_by_count":6,"area":"alignment"},{"id":"2505.23295","title":"How Does Response Length Affect Long-Form Factuality","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2406.00975","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2407.05015","title":"How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions","created":"2024-07-06","cited_by_count":5,"area":null},{"id":"2407.10245","title":"GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?","created":"2024-07-14","cited_by_count":3,"area":"rag"},{"id":"2506.17748","title":"HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2308.11001","title":"Leveraging Explainable AI to Analyze Researchers' Aspect-Based Sentiment about ChatGPT","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2409.14206","title":"AI Assistants for Spaceflight Procedures: Combining Generative Pre-Trained Transformer and Retrieval-Augmented Generation on Knowledge Graphs With Augmented Reality Cues","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2509.00869","title":"Exploring and Mitigating Fawning Hallucinations in Large Language Models","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2511.08916","title":"HalluClean: A Unified Framework to Combat Hallucinations in LLMs","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2512.21422","title":"Teaching People LLM's Errors and Getting it Right","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2607.00447","title":"Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2310.20474","title":"Critical Role of Artificially Intelligent Conversational Chatbot","created":"2023-10-31","cited_by_count":0,"area":null},{"id":"2507.05788","title":"Flippi: End To End GenAI Assistant for E-Commerce","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2605.08863","title":"Max-pooling Network Revisited: Analyzing the Role of Semantic Probability in Multiple Instance Learning for Hallucination Detection","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.00919","title":"Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.07521","title":"Evaluating Hallucinations in Domain-Adapted Large Language Models","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2608.26168","title":"Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":null}