{"total":142,"rows":[{"id":"2411.00348","title":"Attention Tracker: Detecting Prompt Injection Attacks in LLMs","created":"2024-11-01","cited_by_count":95,"area":"safety"},{"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":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2502.17598","title":"Hallucination Detection in LLMs Using Spectral Features of Attention Maps","created":"2025-02-24","cited_by_count":43,"area":null},{"id":"2410.13339","title":"Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval","created":"2024-10-17","cited_by_count":29,"area":"rag"},{"id":"2410.18860","title":"DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations","created":"2024-10-24","cited_by_count":25,"area":null},{"id":"2505.08200","title":"A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs","created":"2025-05-13","cited_by_count":21,"area":null},{"id":"2411.12701","title":"When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations","created":"2024-11-19","cited_by_count":20,"area":"safety"},{"id":"2502.09604","title":"SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models","created":"2025-02-13","cited_by_count":20,"area":"alignment"},{"id":"2504.00711","title":"GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments","created":"2025-04-01","cited_by_count":19,"area":"agents"},{"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":"2501.12934","title":"Correctness Assessment of Code Generated by Large Language Models Using Internal Representations","created":"2025-01-22","cited_by_count":17,"area":null},{"id":"2501.09997","title":"Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models","created":"2025-01-17","cited_by_count":16,"area":"lr"},{"id":"2505.20045","title":"Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads","created":"2025-05-26","cited_by_count":16,"area":null},{"id":"2509.00190","title":"Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics","created":"2025-08-29","cited_by_count":16,"area":"lr"},{"id":"2511.15304","title":"Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models","created":"2025-11-19","cited_by_count":15,"area":"safety"},{"id":"2503.17229","title":"FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs","created":"2025-03-21","cited_by_count":14,"area":null},{"id":"2510.04849","title":"When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA","created":"2025-10-06","cited_by_count":14,"area":null},{"id":"2410.05258","title":"Differential Transformer","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2504.09440","title":"Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection","created":"2025-04-13","cited_by_count":13,"area":"lr"},{"id":"2504.13752","title":"Learning to Attribute with Attention","created":"2025-04-18","cited_by_count":13,"area":null},{"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":"2505.11770","title":"Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2510.12040","title":"Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions","created":"2025-10-14","cited_by_count":11,"area":null},{"id":"2501.03995","title":"RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance","created":"2025-01-07","cited_by_count":10,"area":"mllm"},{"id":"2502.11306","title":"Smoothing Out Hallucinations: Mitigating LLM Hallucination with Smoothed Knowledge Distillation","created":"2025-02-16","cited_by_count":10,"area":"distill"},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"id":"2602.20708","title":"ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction","created":"2026-02-24","cited_by_count":10,"area":"agents"},{"id":"2408.10692","title":"Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models","created":"2024-08-20","cited_by_count":9,"area":null},{"id":"2501.01059","title":"Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2504.14640","title":"Risk Assessment Framework for Code LLMs via Leveraging Internal States","created":"2025-04-20","cited_by_count":9,"area":null},{"id":"2505.16894","title":"Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs","created":"2025-05-22","cited_by_count":9,"area":null},{"id":"2507.23221","title":"A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations","created":"2025-07-31","cited_by_count":9,"area":null},{"id":"2410.01556","title":"Integrative Decoding: Improve Factuality via Implicit Self-consistency","created":"2024-10-02","cited_by_count":8,"area":"lr"},{"id":"2502.13329","title":"Language Models Can Predict Their Own Behavior","created":"2025-02-18","cited_by_count":8,"area":"lr"},{"id":"2502.19964","title":"Do Sparse Autoencoders Generalize? A Case Study of Answerability","created":"2025-02-27","cited_by_count":8,"area":"mechinterp"},{"id":"2508.02419","title":"Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens","created":"2025-08-04","cited_by_count":8,"area":"lr"},{"id":"2601.05547","title":"VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck","created":"2026-01-09","cited_by_count":8,"area":"mllm"},{"id":"2602.08048","title":"TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphs","created":"2026-02-08","cited_by_count":8,"area":"diffusion"},{"id":"2503.12908","title":"HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2504.19457","title":"Towards Long Context Hallucination Detection","created":"2025-04-28","cited_by_count":7,"area":null},{"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":"2510.02671","title":"Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering","created":"2025-10-03","cited_by_count":7,"area":null},{"id":"2502.11193","title":"Large Language Models Penetration in Scholarly Writing and Peer Review","created":"2025-02-16","cited_by_count":6,"area":null},{"id":"2504.04335","title":"Hallucinated Span Detection with Multi-View Attention Features","created":"2025-04-06","cited_by_count":6,"area":null},{"id":"2505.15291","title":"Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization","created":"2025-05-21","cited_by_count":6,"area":null},{"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":"2505.22630","title":"Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2509.24770","title":"Neural Message-Passing on Attention Graphs for Hallucination Detection","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2412.11404","title":"Attention with Dependency Parsing Augmentation for Fine-Grained Attribution","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2505.09031","title":"Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification","created":"2025-05-13","cited_by_count":5,"area":"lr"},{"id":"2510.17733","title":"Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations","created":"2025-10-20","cited_by_count":5,"area":"rag"},{"id":"2511.07694","title":"Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models","created":"2025-11-10","cited_by_count":5,"area":null},{"id":"2602.13699","title":"Gradient-Stable Attention Heads Signal LLM Correctness","created":"2026-02-14","cited_by_count":5,"area":null},{"id":"2605.17877","title":"PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization","created":"2026-05-18","cited_by_count":5,"area":"lr"},{"id":"2605.24919","title":"MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probing","created":"2026-05-24","cited_by_count":5,"area":null},{"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":"2505.16518","title":"CUB: Benchmarking Context Utilisation Techniques for Language Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2509.09700","title":"Cross-Layer Attention Probing for Fine-Grained Hallucination Detection","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2503.03149","title":"DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2503.08963","title":"Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2505.21786","title":"VeriTrail: Closed-Domain Hallucination Detection with Traceability","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2508.19988","title":"AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2512.01909","title":"Latent Debate: A Surrogate Framework for Interpreting LLM Thinking","created":"2025-12-01","cited_by_count":3,"area":"lr"},{"id":"2601.08837","title":"From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda","created":"2025-12-16","cited_by_count":3,"area":"safety"},{"id":"2604.15771","title":"Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing","created":"2026-04-17","cited_by_count":3,"area":"rag"},{"id":"2604.18487","title":"Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety","created":"2026-04-20","cited_by_count":3,"area":"safety"},{"id":"2604.25634","title":"The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2502.13490","title":"What are Models Thinking about? Understanding Large Language Model Hallucinations \"Psychology\" through Model Inner State Analysis","created":"2025-02-19","cited_by_count":2,"area":"lr"},{"id":"2505.23299","title":"Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs","created":"2025-05-29","cited_by_count":2,"area":"rag"},{"id":"2505.24232","title":"From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models","created":"2025-05-30","cited_by_count":2,"area":"safety"},{"id":"2506.02696","title":"Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.18628","title":"AggTruth: Contextual Hallucination Detection using Aggregated Attention Scores in LLMs","created":"2025-06-23","cited_by_count":2,"area":"rag"},{"id":"2601.01552","title":"HalluZig: Hallucination Detection using Zigzag Persistence","created":"2026-01-04","cited_by_count":2,"area":null},{"id":"2602.18145","title":"Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention","created":"2026-02-20","cited_by_count":2,"area":null},{"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":"2605.07209","title":"Hallucination Detection via Activations of Open-Weight Proxy Analyzers","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2606.27679","title":"From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2607.04029","title":"CrossHallu: Do Hallucination Signals Generalize Across Languages and Domains in Large Language Model's Internals?","created":"2026-07-04","cited_by_count":2,"area":null},{"id":"2607.05978","title":"Propose and Attend: Training-free MLLM Grounding Confidence via Multi-Token Localized Attention","created":"2026-07-07","cited_by_count":2,"area":"mllm"},{"id":"2411.03920","title":"RAGulator: Lightweight Out-of-Context Detectors for Grounded Text Generation","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2503.04615","title":"HalluCounter: Reference-free LLM Hallucination Detection in the Wild!","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2503.11346","title":"AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation","created":"2025-03-14","cited_by_count":1,"area":"agents"},{"id":"2504.03302","title":"Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2506.09886","title":"Probabilistic distances-based hallucination detection in LLMs with RAG","created":"2025-06-11","cited_by_count":1,"area":"rag"},{"id":"2509.20065","title":"From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2603.05471","title":"Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval","created":"2026-03-05","cited_by_count":1,"area":"agents"},{"id":"2604.11662","title":"A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.15741","title":"Learning Uncertainty from Sequential Internal Dispersion in Large Language Models","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.15945","title":"RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration","created":"2026-04-17","cited_by_count":1,"area":"rag"},{"id":"2604.22335","title":"Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding","created":"2026-04-24","cited_by_count":1,"area":"safety"},{"id":"2604.26139","title":"HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.05244","title":"Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction","created":"2026-05-04","cited_by_count":1,"area":"rag"},{"id":"2606.15821","title":"The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages","created":"2026-06-14","cited_by_count":1,"area":"mllm"},{"id":"2606.21917","title":"Pre-Generation Hallucination Detection in Large Language Models via Soft-Target Attention Probing","created":"2026-06-20","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":"2607.04683","title":"Failing to See or Failing to Know? Attributing Errors in Vision-Language Models","created":"2026-07-06","cited_by_count":1,"area":"mllm"},{"id":"2607.07670","title":"Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale","created":"2026-07-08","cited_by_count":1,"area":null}],"next_cursor":"100"}