{"total":101,"rows":[{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2501.07861","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","created":"2025-01-14","cited_by_count":32,"area":"lr"},{"id":"2503.23895","title":"Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement","created":"2025-03-31","cited_by_count":25,"area":"rag"},{"id":"2504.14891","title":"Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey","created":"2025-04-21","cited_by_count":20,"area":"rag"},{"id":"2504.10063","title":"Hallucination Detection in LLMs with Topological Divergence on Attention Graphs","created":"2025-04-14","cited_by_count":19,"area":null},{"id":"2505.15962","title":"Pre-training Limited Memory Language Models with Internal and External Knowledge","created":"2025-05-21","cited_by_count":12,"area":null},{"id":"2505.16415","title":"Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation","created":"2025-05-22","cited_by_count":12,"area":"rag"},{"id":"2508.19594","title":"Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs","created":"2025-08-27","cited_by_count":12,"area":"moe"},{"id":"2502.15543","title":"ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation","created":"2025-02-21","cited_by_count":11,"area":"rag"},{"id":"2510.04013","title":"LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2509.15735","title":"EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs","created":"2025-09-19","cited_by_count":10,"area":null},{"id":"2510.19873","title":"From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph","created":"2025-10-22","cited_by_count":10,"area":"lr"},{"id":"2509.21875","title":"LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals","created":"2025-09-26","cited_by_count":9,"area":"rag"},{"id":"2511.08525","title":"Investigating CoT Monitorability in Large Reasoning Models","created":"2025-11-11","cited_by_count":9,"area":"lr"},{"id":"2502.18108","title":"Uncertainty Quantification in Retrieval Augmented Question Answering","created":"2025-02-25","cited_by_count":8,"area":"rag"},{"id":"2510.01274","title":"TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2506.06382","title":"On the Fundamental Impossibility of Hallucination Control in Large Language Models","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2506.12609","title":"Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation","created":"2025-06-14","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":"2512.08892","title":"Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders","created":"2025-12-09","cited_by_count":7,"area":"rag"},{"id":"2504.12560","title":"CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation","created":"2025-04-17","cited_by_count":6,"area":"rag"},{"id":"2505.21072","title":"Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation","created":"2025-05-27","cited_by_count":6,"area":"rag"},{"id":"2507.20930","title":"FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models","created":"2025-07-28","cited_by_count":6,"area":null},{"id":"2512.21577","title":"A Unified Definition of Hallucination: It's The World Model, Stupid!","created":"2025-12-25","cited_by_count":6,"area":"wm"},{"id":"2601.05866","title":"FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG","created":"2026-01-09","cited_by_count":6,"area":"rag"},{"id":"2503.20504","title":"UniVRSE: Unified Vision-conditioned Response Semantic Entropy for Hallucination Detection in Medical Vision-Language Models","created":"2025-03-26","cited_by_count":5,"area":"mllm"},{"id":"2506.21590","title":"Representation Consistency for Accurate and Coherent LLM Answer Aggregation","created":"2025-06-18","cited_by_count":5,"area":"lr"},{"id":"2603.19532","title":"EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models","created":"2026-03-20","cited_by_count":5,"area":null},{"id":"2508.02121","title":"A Survey on AgentOps: Categorization, Challenges, and Future Directions","created":"2025-08-04","cited_by_count":4,"area":"lr"},{"id":"2509.19372","title":"Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2510.13217","title":"LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2505.07528","title":"SEReDeEP: Hallucination Detection in Retrieval-Augmented Models via Semantic Entropy and Context-Parameter Fusion","created":"2025-05-12","cited_by_count":3,"area":"rag"},{"id":"2505.21786","title":"VeriTrail: Closed-Domain Hallucination Detection with Traceability","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2601.11000","title":"When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2602.08013","title":"Small Agent Group is the Future of Digital Health","created":"2026-02-08","cited_by_count":3,"area":"agents"},{"id":"2605.05957","title":"Knowing but Not Correcting: Routine Task Requests Suppress Factual Correction in LLMs","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2605.17028","title":"PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.27786","title":"SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation","created":"2026-06-26","cited_by_count":3,"area":"rag"},{"id":"2606.29431","title":"FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models","created":"2026-06-28","cited_by_count":3,"area":"mllm"},{"id":"2503.16581","title":"Investigating Retrieval-Augmented Generation in Quranic Studies: A Study of 13 Open-Source Large Language Models","created":"2025-03-20","cited_by_count":2,"area":"rag"},{"id":"2503.23415","title":"An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering","created":"2025-03-30","cited_by_count":2,"area":"agents"},{"id":"2510.00508","title":"Copy-Paste to Mitigate Large Language Model Hallucinations","created":"2025-10-01","cited_by_count":2,"area":"rag"},{"id":"2510.14400","title":"MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering","created":"2025-10-16","cited_by_count":2,"area":"alignment"},{"id":"2511.06446","title":"SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention","created":"2025-11-09","cited_by_count":2,"area":null},{"id":"2512.07515","title":"TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG","created":"2025-12-08","cited_by_count":2,"area":"rag"},{"id":"2601.04879","title":"Mind2Report: Expert-Level Commercial Report Synthesis via Cognitive Deep Research Agent","created":"2026-01-08","cited_by_count":2,"area":"agents"},{"id":"2603.21607","title":"INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimation","created":"2026-03-23","cited_by_count":2,"area":"rag"},{"id":"2604.04743","title":"Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2605.03354","title":"What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis","created":"2026-05-05","cited_by_count":2,"area":"agents"},{"id":"2605.08348","title":"How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits","created":"2026-05-08","cited_by_count":2,"area":"mechinterp"},{"id":"2605.11574","title":"Three Regimes of Context-Parametric Conflict: A Predictive Framework and Empirical Validation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.12185","title":"Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2607.22716","title":"Visual Token Compression Enhances Robustness of MLLMs","created":"2026-07-21","cited_by_count":2,"area":"mllm"},{"id":"2504.15630","title":"Exploiting Contextual Knowledge in LLMs through V-usable Information based Layer Enhancement","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2505.24388","title":"ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation","created":"2025-05-30","cited_by_count":1,"area":"lr"},{"id":"2506.15513","title":"RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented Generation","created":"2025-06-18","cited_by_count":1,"area":"rag"},{"id":"2507.04943","title":"ReLoop: \"Seeing Twice and Thinking Backwards\" via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding","created":"2025-07-07","cited_by_count":1,"area":"lr"},{"id":"2509.19643","title":"Human-AI Narrative Synthesis to Foster Shared Understanding in Civic Decision-Making","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2510.12668","title":"Understanding Parametric Knowledge Injection in Retrieval-Augmented Generation","created":"2025-10-14","cited_by_count":1,"area":"rag"},{"id":"2510.21538","title":"InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation","created":"2025-10-24","cited_by_count":1,"area":"rag"},{"id":"2511.12520","title":"TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction","created":"2025-11-16","cited_by_count":1,"area":"lr"},{"id":"2512.09148","title":"Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment","created":"2025-12-09","cited_by_count":1,"area":"rag"},{"id":"2601.14310","title":"CORVUS: Red-Teaming Hallucination Detectors via Internal Signal Camouflage in Large Language Models","created":"2026-01-19","cited_by_count":1,"area":"safety"},{"id":"2601.19245","title":"Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2602.04918","title":"Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.00565","title":"MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs","created":"2026-02-28","cited_by_count":1,"area":"mllm"},{"id":"2603.21925","title":"Guideline-grounded retrieval-augmented generation for ophthalmic clinical decision support","created":"2026-03-23","cited_by_count":1,"area":"rag"},{"id":"2605.20772","title":"VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering","created":"2026-05-20","cited_by_count":1,"area":"mllm"},{"id":"2606.06959","title":"OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2607.04223","title":"Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)","created":"2026-07-05","cited_by_count":1,"area":"rag"},{"id":"2608.06947","title":"When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse","created":"2026-08-07","cited_by_count":1,"area":"rag"},{"id":"2608.18115","title":"Temporal Multi-Signal Fusion for Token-Level Hallucination Detection","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2609.15578","title":"The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive Retrieval","created":"2026-09-14","cited_by_count":1,"area":"rag"},{"id":"2609.16453","title":"Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generation","created":"2026-09-15","cited_by_count":1,"area":"lr"},{"id":"2505.04844","title":"Osiris: A Lightweight Open-Source Hallucination Detection System","created":"2025-05-07","cited_by_count":0,"area":"rag"},{"id":"2508.19614","title":"LFD: Layer Fused Decoding to Exploit External Knowledge in Retrieval-Augmented Generation","created":"2025-08-27","cited_by_count":0,"area":"rag"},{"id":"2511.06073","title":"Stemming Hallucination in Language Models Using a Licensing Oracle","created":"2025-11-08","cited_by_count":0,"area":null},{"id":"2511.10899","title":"From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models","created":"2025-11-14","cited_by_count":0,"area":"lr"},{"id":"2512.11614","title":"Bounding Hallucinations: Merlin-Arthur Protocols for Mutual-Information Bounds in Language Models","created":"2025-12-12","cited_by_count":0,"area":"rag"},{"id":"2512.15068","title":"The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems","created":"2025-12-17","cited_by_count":0,"area":"rag"},{"id":"2603.10195","title":"Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.05348","title":"From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.05025","title":"Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.11330","title":"Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.26362","title":"Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2606.01581","title":"Agent System Operations: Categorization, Challenges, and Future Directions","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2606.05644","title":"FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.01002","title":"Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.02678","title":"DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial","created":"2026-08-02","cited_by_count":0,"area":"rag"},{"id":"2608.07531","title":"Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards","created":"2026-07-24","cited_by_count":0,"area":"agents"},{"id":"2608.11138","title":"Attention-Path Fragility as an Uncertainty Signal in Large Language Models","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.27661","title":"Knowing Before Answering: Decoding Language Models for Reliable RAG","created":"2026-08-27","cited_by_count":0,"area":"rag"},{"id":"2609.05025","title":"Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.08173","title":"Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.08267","title":"Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation","created":"2026-09-08","cited_by_count":0,"area":"rag"},{"id":"2609.08869","title":"OntoKG-EQ: A provenance-grounded, competency-question-governed knowledge graph for auditable analyst querying","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.32964","title":"The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining","created":"2026-09-26","cited_by_count":0,"area":"mechinterp"},{"id":"2609.36813","title":"RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"},{"id":"2609.37700","title":"Locating Answer-Correctness Signals in Frozen Large Language Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01936","title":"Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}