{"total":115,"rows":[{"id":"2503.05613","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","created":"2025-03-07","cited_by_count":76,"area":"mechinterp"},{"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":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48,"area":null},{"id":"2506.18183","title":"Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?","created":"2025-06-22","cited_by_count":38,"area":"lr"},{"id":"2509.10625","title":"No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes","created":"2025-09-12","cited_by_count":38,"area":"mechinterp"},{"id":"2502.11356","title":"SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models","created":"2025-02-17","cited_by_count":34,"area":"mechinterp"},{"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":"2505.16188","title":"SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models","created":"2025-05-22","cited_by_count":29,"area":"mechinterp"},{"id":"2602.02132","title":"There Is More to Refusal in Large Language Models than a Single Direction","created":"2026-02-02","cited_by_count":26,"area":"mechinterp"},{"id":"2504.03022","title":"The Dual-Route Model of Induction","created":"2025-04-03","cited_by_count":24,"area":null},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"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":"2506.06609","title":"Transferring Linear Features Across Language Models With Model Stitching","created":"2025-06-07","cited_by_count":21,"area":"mechinterp"},{"id":"2605.11887","title":"Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models","created":"2026-05-12","cited_by_count":21,"area":"mechinterp"},{"id":"2502.12414","title":"Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2507.20957","title":"Your AI, Not Your View: The Bias of LLMs in Investment Analysis","created":"2025-07-28","cited_by_count":17,"area":null},{"id":"2506.15963","title":"On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy","created":"2025-06-19","cited_by_count":14,"area":"mechinterp"},{"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":"2505.05111","title":"Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders","created":"2025-05-08","cited_by_count":13,"area":"mechinterp"},{"id":"2509.25175","title":"EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering","created":"2025-09-29","cited_by_count":13,"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":"2510.15804","title":"Emergence of Linear Truth Encodings in Language Models","created":"2025-10-17","cited_by_count":12,"area":null},{"id":"2601.05679","title":"Do Sparse Autoencoders Identify Reasoning Features in Language Models?","created":"2026-01-09","cited_by_count":12,"area":"lr"},{"id":"2602.15669","title":"PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra","created":"2026-02-17","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":"2506.10139","title":"Unsupervised Elicitation of Language Models","created":"2025-06-11","cited_by_count":11,"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":"2507.22149","title":"When Truthful Representations Flip Under Deceptive Instructions?","created":"2025-07-29","cited_by_count":10,"area":"mechinterp"},{"id":"2509.23799","title":"Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement","created":"2025-09-28","cited_by_count":10,"area":"mechinterp"},{"id":"2510.03659","title":"Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders","created":"2025-10-04","cited_by_count":10,"area":"mechinterp"},{"id":"2511.20820","title":"SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models","created":"2025-11-25","cited_by_count":10,"area":"agents"},{"id":"2505.14530","title":"Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs","created":"2025-05-20","cited_by_count":9,"area":"lr"},{"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":"2506.07971","title":"CyberV: Cybernetics for Test-time Scaling in Video Understanding","created":"2025-06-09","cited_by_count":8,"area":"lr"},{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2502.14445","title":"PredictaBoard: Benchmarking LLM Score Predictability","created":"2025-02-20","cited_by_count":7,"area":null},{"id":"2504.15133","title":"EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models","created":"2025-04-21","cited_by_count":7,"area":"mechinterp"},{"id":"2512.08892","title":"Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders","created":"2025-12-09","cited_by_count":7,"area":"rag"},{"id":"2602.05859","title":"DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders","created":"2026-02-05","cited_by_count":7,"area":"diffusion"},{"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":"2509.14223","title":"Fresh in memory: Training-order recency is linearly encoded in language model activations","created":"2025-09-17","cited_by_count":6,"area":null},{"id":"2510.02324","title":"Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning","created":"2025-09-25","cited_by_count":6,"area":"moe"},{"id":"2602.12418","title":"Sparse Autoencoders are Capable LLM Jailbreak Mitigators","created":"2026-02-12","cited_by_count":6,"area":"safety"},{"id":"2604.19974","title":"Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders","created":"2026-04-21","cited_by_count":6,"area":"mechinterp"},{"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":"2507.17257","title":"Agent Identity Evals: Measuring Agentic Identity","created":"2025-07-23","cited_by_count":5,"area":"agents"},{"id":"2510.02917","title":"Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders","created":"2025-10-03","cited_by_count":5,"area":"mechinterp"},{"id":"2512.07730","title":"SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination","created":"2025-12-08","cited_by_count":5,"area":"mllm"},{"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":"2509.09700","title":"Cross-Layer Attention Probing for Fine-Grained Hallucination Detection","created":"2025-09-04","cited_by_count":4,"area":null},{"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":"2510.01246","title":"A Comparative Analysis of Sparse Autoencoder and Activation Difference in Language Model Steering","created":"2025-09-24","cited_by_count":4,"area":"mechinterp"},{"id":"2510.15551","title":"Rethinking Cross-lingual Gaps from a Statistical Viewpoint","created":"2025-10-17","cited_by_count":4,"area":"lr"},{"id":"2601.16766","title":"Do LLM hallucination detectors suffer from low-resource effect?","created":"2026-01-23","cited_by_count":4,"area":null},{"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":"2605.22658","title":"SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation","created":"2026-05-21","cited_by_count":4,"area":"lr"},{"id":"2505.16612","title":"Steering Large Language Models for Machine Translation Personalization","created":"2025-05-22","cited_by_count":3,"area":"mechinterp"},{"id":"2509.15631","title":"Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models","created":"2025-09-19","cited_by_count":3,"area":"safety"},{"id":"2511.07001","title":"SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMs","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2512.01909","title":"Latent Debate: A Surrogate Framework for Interpreting LLM Thinking","created":"2025-12-01","cited_by_count":3,"area":"lr"},{"id":"2512.24560","title":"Localized Calibrated Uncertainty in Code Language Models","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2601.15334","title":"No Reliable Evidence of Self-Reported Sentience in Small Large Language Models","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2602.00621","title":"Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering","created":"2026-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2603.05881","title":"Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.12373","title":"Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness","created":"2026-04-14","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":"2606.01479","title":"Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech","created":"2026-05-31","cited_by_count":3,"area":"mechinterp"},{"id":"2504.02865","title":"The Illusionist's Prompt: Exposing the Factual Vulnerabilities of Large Language Models with Linguistic Nuances","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2505.12182","title":"Truth Neurons","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2505.14420","title":"SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection","created":"2025-05-20","cited_by_count":2,"area":"mechinterp"},{"id":"2505.21399","title":"Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2507.14894","title":"SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs","created":"2025-07-20","cited_by_count":2,"area":"mechinterp"},{"id":"2510.20690","title":"Neural Diversity Regularizes Hallucinations in Language Models","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2510.26935","title":"RepV: Safety-Separable Latent Spaces for Scalable Neurosymbolic Plan Verification","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2601.11019","title":"Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs","created":"2026-01-16","cited_by_count":2,"area":"mechinterp"},{"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":"2603.10771","title":"Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.15557","title":"Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models","created":"2026-03-16","cited_by_count":2,"area":"mllm"},{"id":"2605.28567","title":"Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression","created":"2026-05-27","cited_by_count":2,"area":"mechinterp"},{"id":"2606.11105","title":"PhantomBench: Benchmarking the Non-existential Threat of Language Models","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2607.04277","title":"Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement","created":"2026-07-05","cited_by_count":2,"area":"synth"},{"id":"2507.06722","title":"On the Effect of Uncertainty on Layer-wise Inference Dynamics","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2510.04048","title":"Increasing LLM response trustworthiness using voting ensembles","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2510.09421","title":"On the Representations of Entities in Auto-regressive Large Language Models","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2601.11429","title":"Relational Linearity is a Predictor of Hallucinations","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2602.07311","title":"LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery","created":"2026-02-07","cited_by_count":1,"area":"mechinterp"},{"id":"2603.18446","title":"UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.03532","title":"LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering","created":"2026-04-04","cited_by_count":1,"area":"mechinterp"},{"id":"2606.08496","title":"SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization","created":"2026-06-07","cited_by_count":1,"area":"alignment"},{"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},{"id":"2608.18115","title":"Temporal Multi-Signal Fusion for Token-Level Hallucination Detection","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.28018","title":"Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning","created":"2026-08-28","cited_by_count":1,"area":"lr"},{"id":"2510.08613","title":"GraphGhost: Tracing Structures Behind Large Language Models","created":"2025-10-07","cited_by_count":0,"area":"lr"},{"id":"2601.17728","title":"Unsupervised Elicitation of Moral Values from Language Models","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2602.09486","title":"Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.22453","title":"Identifying Crucial Attention Heads for Multilingual Language Models: Retrieval and Retrieval-Transition Heads","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2604.25167","title":"From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models","created":"2026-04-28","cited_by_count":0,"area":"mechinterp"},{"id":"2604.26866","title":"MoRFI: Monotonic Sparse Autoencoder Feature Identification","created":"2026-04-29","cited_by_count":0,"area":"mechinterp"},{"id":"2605.00123","title":"Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models","created":"2026-04-30","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}