{"total":131,"rows":[{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085,"area":"mechinterp"},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332,"area":null},{"id":"2401.01313","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","created":"2024-01-02","cited_by_count":269,"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":"2401.06855","title":"Fine-grained Hallucination Detection and Editing for Language Models","created":"2024-01-12","cited_by_count":149,"area":null},{"id":"2406.04744","title":"CRAG -- Comprehensive RAG Benchmark","created":"2024-06-07","cited_by_count":97,"area":"rag"},{"id":"2311.07914","title":"Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey","created":"2023-11-14","cited_by_count":92,"area":null},{"id":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66,"area":null},{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63,"area":"moe"},{"id":"2402.09733","title":"Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States","created":"2024-02-15","cited_by_count":52,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2407.01178","title":"$\\text{Memory}^3$: Language Modeling with Explicit Memory","created":"2024-07-01","cited_by_count":40,"area":"rag"},{"id":"2410.21943","title":"Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications","created":"2024-10-29","cited_by_count":31,"area":"rag"},{"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":"2311.18580","title":"FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity","created":"2023-11-30","cited_by_count":25,"area":null},{"id":"2406.09815","title":"Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments","created":"2024-06-14","cited_by_count":25,"area":"rag"},{"id":"2401.07702","title":"Prompting open-source and commercial language models for grammatical error correction of English learner text","created":"2024-01-15","cited_by_count":24,"area":null},{"id":"2311.15296","title":"UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation","created":"2023-11-26","cited_by_count":22,"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":"2503.00751","title":"RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery","created":"2025-03-02","cited_by_count":19,"area":"rag"},{"id":"2506.10408","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","created":"2025-06-12","cited_by_count":19,"area":"lr"},{"id":"2504.10074","title":"MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework","created":"2025-04-14","cited_by_count":18,"area":"mllm"},{"id":"2404.07461","title":"An Audit on the Perspectives and Challenges of Hallucinations in NLP","created":"2024-04-11","cited_by_count":17,"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":"2510.00296","title":"Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT","created":"2025-09-30","cited_by_count":17,"area":null},{"id":"2507.21017","title":"MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them","created":"2025-07-28","cited_by_count":16,"area":"agents"},{"id":"2408.13808","title":"Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models","created":"2024-08-25","cited_by_count":15,"area":null},{"id":"2410.04241","title":"Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations","created":"2024-10-05","cited_by_count":15,"area":null},{"id":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2312.06798","title":"Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2410.01036","title":"MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages","created":"2024-10-01","cited_by_count":14,"area":null},{"id":"2403.09442","title":"LLM-based agents for automating the enhancement of user story quality: An early report","created":"2024-03-14","cited_by_count":13,"area":"agents"},{"id":"2410.16638","title":"LLMScan: Causal Scan for LLM Misbehavior Detection","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2502.19844","title":"ProAPO: Progressively Automatic Prompt Optimization for Visual Classification","created":"2025-02-27","cited_by_count":13,"area":"mllm"},{"id":"2503.14749","title":"Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence","created":"2025-03-18","cited_by_count":13,"area":null},{"id":"2404.03745","title":"Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2410.01691","title":"FactAlign: Long-form Factuality Alignment of Large Language Models","created":"2024-10-02","cited_by_count":12,"area":"alignment"},{"id":"2503.14043","title":"Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2403.17306","title":"Visual Hallucination: Definition, Quantification, and Prescriptive Remediations","created":"2024-03-26","cited_by_count":11,"area":null},{"id":"2404.17733","title":"Building a Large Japanese Web Corpus for Large Language Models","created":"2024-04-27","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":"2410.17234","title":"Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy","created":"2024-10-22","cited_by_count":11,"area":null},{"id":"2403.19113","title":"FACTOID: FACtual enTailment fOr hallucInation Detection","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2510.13975","title":"Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systems","created":"2025-10-15","cited_by_count":10,"area":"rag"},{"id":"2402.17982","title":"Collaborative decoding of critical tokens for boosting factuality of large language models","created":"2024-02-28","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":"2401.00280","title":"Advancing TTP Analysis: Harnessing the Power of Large Language Models with Retrieval Augmented Generation","created":"2023-12-30","cited_by_count":8,"area":"rag"},{"id":"2410.09770","title":"'Quis custodiet ipsos custodes?' Who will watch the watchmen? On Detecting AI-generated peer-reviews","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2510.08602","title":"Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection","created":"2025-10-07","cited_by_count":8,"area":null},{"id":"2404.16478","title":"Evaluating Consistency and Reasoning Capabilities of Large Language Models","created":"2024-04-25","cited_by_count":7,"area":"lr"},{"id":"2410.14262","title":"Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation","created":"2024-10-18","cited_by_count":7,"area":"agents"},{"id":"2502.11916","title":"EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models","created":"2025-02-17","cited_by_count":7,"area":"mllm"},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2402.16211","title":"HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMs","created":"2024-02-25","cited_by_count":6,"area":"alignment"},{"id":"2410.17406","title":"ProveRAG: Provenance-Driven Vulnerability Analysis with Automated Retrieval-Augmented LLMs","created":"2024-10-22","cited_by_count":6,"area":"rag"},{"id":"2506.15065","title":"HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models","created":"2025-06-18","cited_by_count":6,"area":"agents"},{"id":"2509.24770","title":"Neural Message-Passing on Attention Graphs for Hallucination Detection","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2510.24222","title":"HACK: Hallucinations Along Certainty and Knowledge Axes","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2403.17536","title":"ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler","created":"2024-03-26","cited_by_count":5,"area":null},{"id":"2405.18344","title":"The Battle of LLMs: A Comparative Study in Conversational QA Tasks","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2406.18114","title":"Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis","created":"2024-06-26","cited_by_count":5,"area":"rag"},{"id":"2407.08819","title":"Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladin","created":"2024-07-11","cited_by_count":5,"area":null},{"id":"2408.10490","title":"Analysis of Plan-based Retrieval for Grounded Text Generation","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2409.11589","title":"ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering","created":"2024-09-17","cited_by_count":5,"area":null},{"id":"2502.04043","title":"Probe-Free Low-Rank Activation Intervention","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2502.10420","title":"Position: Stop Acting Like Language Model Agents Are Normal Agents","created":"2025-02-04","cited_by_count":5,"area":"agents"},{"id":"2607.28374","title":"LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"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":"2411.09255","title":"DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2506.07309","title":"ConfRAG: Confidence-Guided Retrieval-Augmenting Generation","created":"2025-06-08","cited_by_count":4,"area":"rag"},{"id":"2507.15286","title":"Beyond Easy Wins: A Text Hardness-Aware Benchmark for LLM-generated Text Detection","created":"2025-07-21","cited_by_count":4,"area":null},{"id":"2602.08159","title":"The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models","created":"2026-02-08","cited_by_count":4,"area":"mechinterp"},{"id":"2608.01021","title":"Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarking","created":"2026-08-02","cited_by_count":4,"area":null},{"id":"2504.01153","title":"Catch Me if You Search: When Contextual Web Search Results Affect the Detection of Hallucinations","created":"2025-04-01","cited_by_count":3,"area":null},{"id":"2509.25498","title":"Not Wrong, But Untrue: LLM Overconfidence in Document-Based Queries","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2604.17284","title":"HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents","created":"2026-04-19","cited_by_count":3,"area":"agents"},{"id":"2403.18976","title":"\"Sorry, Come Again?\" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2407.02028","title":"Why does in-context learning fail sometimes? Evaluating in-context learning on open and closed questions","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2410.23769","title":"The Potential of LLMs in Medical Education: Generating Questions and Answers for Qualification Exams","created":"2024-10-31","cited_by_count":2,"area":null},{"id":"2412.17614","title":"Emerging Security Challenges of Large Language Models","created":"2024-12-23","cited_by_count":2,"area":null},{"id":"2501.07824","title":"Efficient Real-time Refinement of Language Model Text Generation","created":"2025-01-14","cited_by_count":2,"area":null},{"id":"2501.15758","title":"Distributional Surgery for Language Model Activations","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2503.17965","title":"Understanding the Effects of RLHF on the Quality and Detectability of LLM-Generated Texts","created":"2025-03-23","cited_by_count":2,"area":"alignment"},{"id":"2505.00557","title":"Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2505.10792","title":"Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation","created":"2025-05-16","cited_by_count":2,"area":"rag"},{"id":"2505.16849","title":"Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks","created":"2025-05-22","cited_by_count":2,"area":"lr"},{"id":"2506.12100","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2509.04820","title":"Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation","created":"2025-09-05","cited_by_count":2,"area":"rag"},{"id":"2509.07939","title":"Guided Reasoning in LLM-Driven Penetration Testing Using Structured Attack Trees","created":"2025-09-09","cited_by_count":2,"area":"lr"},{"id":"2509.18156","title":"Event Causality Identification with Synthetic Control","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2511.21066","title":"Context-Aware Pragmatic Metacognitive Prompting for Sarcasm Detection","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2512.02329","title":"Towards autonomous normative multi-agent systems for Human-AI software engineering teams","created":"2025-12-02","cited_by_count":2,"area":"agents"},{"id":"2512.19570","title":"The Epistemological Consequences of Large Language Models: Rethinking collective intelligence and institutional knowledge","created":"2025-12-22","cited_by_count":2,"area":"lr"},{"id":"2601.20105","title":"FFE-Hallu:Hallucinations in Fixed Figurative Expressions:Benchmark of Idioms and Proverbs in the Persian Language","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2602.02018","title":"Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.10437","title":"Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features","created":"2026-02-11","cited_by_count":2,"area":"mechinterp"},{"id":"2605.13737","title":"Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2401.08273","title":"Large Language Models are Null-Shot Learners","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2410.12380","title":"Evaluation of Attribution Bias in Generator-Aware Retrieval-Augmented Large Language Models","created":"2024-10-16","cited_by_count":1,"area":"rag"},{"id":"2503.15985","title":"Exploring the Reliability of Self-explanation and its Relationship with Classification in Language Model-driven Financial Analysis","created":"2025-03-20","cited_by_count":1,"area":null}],"next_cursor":"100"}