LLM Interpretability

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

57 papers in the last four weeks, up 73% on the four weeks before. 0.6% of all new papers.

Jul 13Week of Sep 28

Latest papers 546

All topics

Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination
Jun 30, 2026Vijay Vankadaru, Asha Matthews, Tanya Roosta +1LLM Hallucination Mitigation LLM Interpretability
School of Information University of California, Berkeley California, USA
Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust
Jun 30, 2026Nishant SubramaniLanguage Model Steering LLM Interpretability
Carnegie Mellon University, Language Technologies Institute
Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision
Jun 30, 2026Zifan Carl Guo, Laura Ruis, Jacob Andreas +1Counterfactual Explanations Faithfulness of Language Model Explanations
MIT EECS
Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?
Jun 30, 2026Philippe Chlenski, Zachariah Carmichael, Ayush Warikoo +5Faithfulness of Language Model Explanations LLM Interpretability
1Meta.
C $^{2}$ R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders
Jun 29, 2026Haoran Jin, Xiting Wang, Shijie Ren +2LLM Interpretability Representation Disentanglement
University of Science and Technology of China · State Key Laboratory of Cognitive Intelligence · Gaoling School of Artificial Intelligence, Renmin University of China
Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression
Jun 29, 2026Shuochen Chang, Qingyang Liu, Shaobo Wang +8LLM Interpretability Efficient Language Model Reasoning
Shanghai Jiao Tong University · Tongji University
Mechanistically Eliciting Latent Behaviors in Language Models
Jun 28, 2026Andrew Mack, Nina Panickssery, Alexander Matt TurnerLLM Alignment Language Model Safety Evaluation
†Principles of Intelligence · ‡Anthropic · §Independent
Reported Confidence in LLMs Tracks Commitment More Than Correctness
Jun 28, 2026Dharshan KumaranConfidence Estimation in Language Models LLM Interpretability
Google DeepMind
Representational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Models
Jun 28, 2026Archit ManekLLM Interpretability Language Model Scaling Laws
Independent Researcher.
The strength of clinical evidence is recoverable from language model representations but not from their stated grades
Jun 27, 2026Soroosh Tayebi ArastehLLM Interpretability Language Model Calibration
Lab for AI in Medicine, RWTH Aachen University, Aachen, Germany · Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen · Department of Urology, Stanford University, Stanford, CA, USA +1
Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions
Jun 27, 2026David Courtis, Ting HuLanguage Model Steering LLM Interpretability
Department of Computing, Queen’s University Kingston, Kingston, ON, Canada.
What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs
Jun 26, 2026Nhi Nguyen, Shauli Ravfogel, Rajesh RanganathLLM Evaluation LLM Interpretability
New York University
Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution
Jun 26, 2026Kevin Der, Harish Kamath, Ben ThompsonLLM Interpretability Sparse Autoencoders
Anthropic Fellows Program · Anthropic
VASAE: Naming SAE Dictionary Directions with Vocabulary-Aligned Anchoring
Jun 26, 2026Kairui Zhang, Ziwen Yu, Zahraa S. Abdallah +1LLM Interpretability Sparse Autoencoders
Intelligent Systems Laboratory, University of Bristol, Bristol, UK · University of Bristol, Bristol, UK · University of Amsterdam, Amsterdam, Netherlands
LMs as Task-Specific Knowledge Bases: An Interpretability Analysis
Jun 25, 2026Amit Elhelo, Amir Globerson, Mor GevaLLM Interpretability Factual Knowledge in Language Models
Blavatnik School of Computer Science and AI, Tel Aviv University · Google Research
Forecasting With LLMs: Improved Generalization Through Feature Steering
Jun 25, 2026Humzah Merchant, Bradford LevyLanguage Model Steering LLM Interpretability
University of Chicago, Illinois, United States.
Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs
Jun 25, 2026Sinie van der Ben, Raphaël Baur, Yannick Metz +1LLM Interpretability Valence-Arousal Modeling
Department of Computer Science, ETH, Zurich, Switzerland.
Discovering Millions of Interpretable Features with Sparse Autoencoders
Jun 25, 2026XinYang He, Wei Wang, Bing Zhao +5LLM Interpretability Sparse Autoencoders
AI DATA, Alibaba Group Holding Limited · Beijing Institute of Technology
Localizing RL-Induced Tool Use to a Single Crosscoder Feature
Jun 25, 2026Andrii Shportko, Shubham Bhokare, Ahmed Zeyad A Alzahrani +3LLM Interpretability LLM Tool Use
1Northwestern University.
What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics
Jun 23, 2026Sofiia Nikolenko, Michele Papucci, Mina Rezaei +1LLM Interpretability LLM Jailbreak Attacks
LMU Munich, Munich, Germany · relAI – Konrad Zuse School of Excellence in Reliable AI · University of Pisa, Pisa, Italy +2
Detecting and Controlling Sycophancy with Cascading Linear Features
Jun 23, 2026Maty Bohacek, Rishub Jain, Nicholas Dufour +3LLM Sycophancy Language Model Steering
Stanford University · Google DeepMind
Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration
Jun 23, 2026Pietro Tropeano, Maria Maistro, Tuukka Ruotsalo +1LLM Pruning LLM Interpretability
University of Copenhagen Copenhagen, Denmark · LUT University Lahti, Finland
Evidence for feature-specific error correction in LLMs
Jun 23, 2026Francisco Ferreira da Silva, Stefan HeimersheimLLM Interpretability Language Model Robustness
Pivotal Research.
Probing the Misaligned Thinking Process of Language Models
Jun 23, 2026Kaiwen Zhou, Constantin Venhoff, Jonathan Michala +2LLM Alignment LLM Auditing
1Anthropic Fellows · 2MATS · 3UCSC +2
Sentence-Level Contextual Entrainment in Large Language Models
Jun 23, 2026Yang Liu, Chenhui ChuLLM Interpretability
Kyoto University
Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior
Jun 22, 2026Christopher J. Anders, Henrique Da Silva Gameiro, Nico Daheim +1LLM Auditing LLM Interpretability
RIKEN Center for Advanced Intelligence Project, Tokyo, Japan · Section of Computer Science, EPFL Lausanne, Switzerland · Ubiquitous Knowledge Processing Lab (UKP Lab),2026 Department of Computer Science, Technical University of Darmstadt +2
Evaluation Awareness Is Not One Capability: Evidence from Open Language Models
Jun 22, 2026Nilesh Nayan, Aishwarya Sampath Kumar, Rishiraj Girmal +5Language Model Safety Evaluation LLM Interpretability
University of Massachusetts, Amherst · 2Microsoft Corp.
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
Jun 22, 2026Jun Zhang, Jiasheng Zheng, Boxi Cao +5LLM Auditing LLM Interpretability
Chinese Information Processing Laboratory Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences
Abstract representational geometry supports inference in large language models
Jun 22, 2026Yunan Zeng, Yuwang WangLLM Inference LLM Interpretability
College of Future Information Technology, Fudan University, Shanghai, 200433, China · Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, 100084, China
Exposing the Illusion of Erasure in Knowledge Editing for LLMs
Jun 22, 2026Advik Raj Basani, Anshuman ChhabraKnowledge Editing Knowledge Conflicts in Language Models
Birla Institute of Technology and Science, Goa · University of South Florida

Jun 30, 2026, cs.CLJ/K move · Enter open · S save

Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination

Vijay Vankadaru, Asha Matthews, Tanya Roosta, Peyman Passban

School of Information University of California, Berkeley California, USA

LLM Hallucination Mitigation LLM Interpretability LLM Hallucination Detection Causal Interventions in Language Models Medical LLMs

Open paper AskPDF arXiv

Hallucination remains one of the central obstacles to deploying medical LLMs. Yet, even when hallucination can be detected, it is still unclear whether the internal representations associated with it can be used for control rather than detection alone. Using four open-source models across a suite of medical question-answering datasets, we show that a simple, carefully conditioned probe can reliably detect hallucination, with AUROC scores between 0.77 and 0.86 in our case. We further show that this signal is distributed and redundant rather than narrowly localized. Systematically selected neurons outperform random neurons only at very small subset sizes, whereas random subsets of a few hundred neurons recover nearly the full signal, and low-dimensional random projections preserve most of the detection performance. Beyond detection, we test whether this representation is causally actionable. Across 16 model--dataset combinations, our results reveal a sharp gap between decodability and controllability. The same internal structure that makes hallucination easy to detect does not translate into reliable neuron-level control. These findings show that medical hallucination seems to be readily visible in internal activations, but not easily corrected by steering the neurons most associated with it. More broadly, our results suggest that hallucination mitigation is not simply a matter of identifying the right neurons, and point to a deeper separation between what representations reveal and what they allow us to change.

Momentum

Related topics

Latest papers 546