{"total":244,"rows":[{"id":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","cited_by_count":225,"area":"lr"},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117,"area":"lr"},{"id":"2502.06233","title":"Confidence Improves Self-Consistency in LLMs","created":"2025-02-10","cited_by_count":113,"area":"lr"},{"id":"2410.11779","title":"MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation","created":"2024-10-15","cited_by_count":88,"area":"mllm"},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2501.06346","title":"Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages","created":"2025-01-10","cited_by_count":59,"area":null},{"id":"2502.01839","title":"Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification","created":"2025-02-03","cited_by_count":50,"area":"lr"},{"id":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48,"area":null},{"id":"2503.19213","title":"A Survey of Large Language Model Agents for Question Answering","created":"2025-03-24","cited_by_count":48,"area":"agents"},{"id":"2509.03531","title":"Real-Time Detection of Hallucinated Entities in Long-Form Generation","created":"2025-08-26","cited_by_count":34,"area":null},{"id":"2507.16488","title":"ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs","created":"2025-07-22","cited_by_count":32,"area":null},{"id":"2501.01306","title":"Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking","created":"2025-01-02","cited_by_count":31,"area":"lr"},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27,"area":null},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2502.17214","title":"CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought","created":"2025-02-24","cited_by_count":23,"area":"lr"},{"id":"2508.08285","title":"The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","cited_by_count":19,"area":null},{"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":"2505.17656","title":"Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs","created":"2025-05-23","cited_by_count":18,"area":null},{"id":"2507.12379","title":"Probing for Arithmetic Errors in Language Models","created":"2025-07-16","cited_by_count":18,"area":null},{"id":"2412.02186","title":"VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding","created":"2024-12-03","cited_by_count":17,"area":"lr"},{"id":"2507.09709","title":"Large Language Models Encode Semantics and Alignment in Linearly Separable Representations","created":"2025-07-13","cited_by_count":17,"area":"safety"},{"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":"2511.04418","title":"The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity","created":"2025-11-06","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":"2504.20271","title":"Investigating task-specific prompts and sparse autoencoders for activation monitoring","created":"2025-04-28","cited_by_count":15,"area":"mechinterp"},{"id":"2504.01205","title":"Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2603.05465","title":"HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token","created":"2026-03-05","cited_by_count":14,"area":"mllm"},{"id":"2504.14379","title":"The Geometry of Self-Verification in a Task-Specific Reasoning Model","created":"2025-04-19","cited_by_count":13,"area":"lr"},{"id":"2508.15882","title":"Beyond Transcription: Mechanistic Interpretability in ASR","created":"2025-08-21","cited_by_count":13,"area":"mechinterp"},{"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":"2510.15804","title":"Emergence of Linear Truth Encodings in Language Models","created":"2025-10-17","cited_by_count":12,"area":null},{"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":"2510.04013","title":"LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2505.23657","title":"Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation","created":"2025-05-29","cited_by_count":10,"area":null},{"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":"2510.09033","title":"Do LLMs Really Know What They Don't Know? Internal States Mainly Reflect Knowledge Recall Rather Than Truthfulness","created":"2025-10-10","cited_by_count":10,"area":null},{"id":"2503.08216","title":"Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation","created":"2025-03-11","cited_by_count":9,"area":"mllm"},{"id":"2506.08572","title":"The Geometries of Truth Are Orthogonal Across Tasks","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2507.17394","title":"HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2510.11905","title":"LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2603.02203","title":"Tool Verification for Test-Time Reinforcement Learning","created":"2026-03-02","cited_by_count":9,"area":"lr"},{"id":"2604.19018","title":"Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control","created":"2026-04-21","cited_by_count":9,"area":"alignment"},{"id":"2412.01250","title":"Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues","created":"2024-12-02","cited_by_count":8,"area":"agents"},{"id":"2503.22215","title":"Learning to Instruct for Visual Instruction Tuning","created":"2025-03-28","cited_by_count":8,"area":null},{"id":"2505.13529","title":"BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs","created":"2025-05-18","cited_by_count":8,"area":"lr"},{"id":"2509.14478","title":"Estimating Semantic Alphabet Size for LLM Uncertainty Quantification","created":"2025-09-17","cited_by_count":8,"area":null},{"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":"2601.03042","title":"BaseCal: Unsupervised Confidence Calibration via Base Model Signals","created":"2026-01-06","cited_by_count":8,"area":null},{"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":"2602.20273","title":"The Truthfulness Spectrum Hypothesis","created":"2026-02-23","cited_by_count":8,"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":"2510.20176","title":"Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding","created":"2025-10-23","cited_by_count":7,"area":"agents"},{"id":"2604.15574","title":"Why Fine-Tuning Encourages Hallucinations and How to Fix It","created":"2026-04-16","cited_by_count":7,"area":"distill"},{"id":"2605.00737","title":"To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling","created":"2026-05-01","cited_by_count":7,"area":"agents"},{"id":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2608.02657","title":"Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States","created":"2026-08-01","cited_by_count":7,"area":"agents"},{"id":"2502.08663","title":"Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysis","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2505.16170","title":"When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2505.23295","title":"How Does Response Length Affect Long-Form Factuality","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2506.00088","title":"HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2507.02197","title":"Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust","created":"2025-07-02","cited_by_count":6,"area":"agents"},{"id":"2509.23782","title":"Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions","created":"2025-09-28","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":"2510.19496","title":"CARES: Context-Aware Resolution Selector for VLMs","created":"2025-10-22","cited_by_count":6,"area":"mllm"},{"id":"2510.24222","title":"HACK: Hallucinations Along Certainty and Knowledge Axes","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2512.03994","title":"Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs","created":"2025-12-03","cited_by_count":6,"area":null},{"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":"2603.02913","title":"Eliciting Numerical Predictive Distributions of LLMs Without Autoregression","created":"2026-03-03","cited_by_count":6,"area":null},{"id":"2603.17199","title":"Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2604.20817","title":"Convergent Evolution: How Different Language Models Learn Similar Number Representations","created":"2026-04-22","cited_by_count":6,"area":null},{"id":"2607.07003","title":"Dissociating the Internal Representations of Sycophancy in LLMs","created":"2026-07-08","cited_by_count":6,"area":"mechinterp"},{"id":"2506.00074","title":"Whose Name Comes Up? Auditing LLM-Based Scholar Recommendations","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2508.08139","title":"Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models","created":"2025-08-11","cited_by_count":5,"area":"agents"},{"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":"2602.10092","title":"Quantum-Audit: Evaluating the Reasoning Limits of LLMs on Quantum Computing","created":"2026-02-10","cited_by_count":5,"area":"lr"},{"id":"2602.21054","title":"VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation","created":"2026-02-24","cited_by_count":5,"area":"mllm"},{"id":"2604.16430","title":"HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders","created":"2026-04-06","cited_by_count":5,"area":"mechinterp"},{"id":"2604.24881","title":"Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate","created":"2026-04-27","cited_by_count":5,"area":"lr"},{"id":"2605.01428","title":"Hallucinations Undermine Trust; Metacognition is a Way Forward","created":"2026-05-02","cited_by_count":5,"area":null},{"id":"2605.24919","title":"MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probing","created":"2026-05-24","cited_by_count":5,"area":null},{"id":"2411.08254","title":"Toward Automated Validation of Language Model Synthesized Test Cases using Semantic Entropy","created":"2024-11-13","cited_by_count":4,"area":null},{"id":"2502.12476","title":"CoCo-CoLa: Evaluating and Improving Language Adherence in Multilingual LLMs","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2505.15386","title":"RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2505.15793","title":"HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving","created":"2025-05-21","cited_by_count":4,"area":"driving"},{"id":"2506.01042","title":"Probing Neural Topology of Large Language Models","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2507.08371","title":"The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality","created":"2025-07-11","cited_by_count":4,"area":"synth"},{"id":"2509.24678","title":"Reference-Free Rating of LLM Responses via Latent Information","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2512.17601","title":"HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection","created":"2025-12-19","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":"2604.01457","title":"Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2605.07153","title":"Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2607.06503","title":"Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade","created":"2026-07-07","cited_by_count":4,"area":"agents"},{"id":"2503.02851","title":"Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layers","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2505.08662","title":"Revealing economic facts: LLMs know more than they say","created":"2025-05-13","cited_by_count":3,"area":null},{"id":"2505.11741","title":"MTRE: Multi-Token Reliability Estimation for Hallucination Detection in VLMs","created":"2025-05-16","cited_by_count":3,"area":"mllm"},{"id":"2505.15075","title":"Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs","created":"2025-05-21","cited_by_count":3,"area":"mllm"},{"id":"2508.12632","title":"Prompt-Induced Linguistic Fingerprints for LLM-Generated Fake News Detection","created":"2025-08-18","cited_by_count":3,"area":null},{"id":"2510.06107","title":"Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models","created":"2025-10-07","cited_by_count":3,"area":null}],"next_cursor":"100"}