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

Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations
Jun 21, 2026Dongyub Jude Lee, Jungseob Lee, Seungyoon Lee +5LLM Interpretability LLM Fine-Tuning
Zoom Communications · Korea University · Yonsei University +1
Agent MechSuits: Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents
Jun 21, 2026Weidi Luo, Qiming Zhang, Yihao Quan +5Computer-Use Agents LLM Interpretability
University of Georgia · University of South Florida · Rutgers University +3
Interleaved Speech Language Models Latently Work In Text
Jun 21, 2026Talia Sternberg, Gallil Maimon, Yossi AdiLLM Interpretability Speech Language Models
The Hebrew University of Jerusalem
Words as Difference Makers: How Large Language Models Determine Causal Structure in Text
Jun 21, 2026Wolfgang PietschCausal World Models LLM Interpretability
tum
First-Token Broadcasters: Mechanistic Origins of Language Identity and Distributed Robustness in Transformers
Jun 21, 2026Arjun Pillai, Christian Hoang, Anjelo Jann LarozaMultilingual Language Models LLM Interpretability
1Irvington High School · 2GenAI4E · 3Mapua University
Interpreting Latent CoT Reasoning as Dynamical Systems
Jun 20, 2026Sabari Iyyappan Duraipandian, Shreya Sanjay Boyane, Manju Nagesh +3Latent Dynamics Modeling LLM Interpretability
1San Jose State University. · 2Worcester Polytechnic Institute. · 3George Mason University. +1
Local Causal Attribution of Chain-of-Thought Reasoning
Jun 20, 2026Dennis Wei, Yannis Belkhiter, Erik Miehling +1LLM Interpretability Causal Attribution
1IBM Research.
Decodable but Not Faithful: Coupling Natural-Language Rationales to Programmatic Verifiers
Jun 19, 2026Vatsal Ananthula, Adarsh KumarappanFaithfulness of Language Model Explanations LLM Auditing
University of California, Berkeley · 2California Institute of Technology
Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models
Jun 19, 2026Zhiqing Yang, Yilun Liu, Yunpu Ma +2Multilingual Language Model Evaluation LLM Interpretability
Ludwig Maximilian University of Munich · Munich Center for Machine Learning
Factual Retrieval in LLMs Is a Redundant, Distributed and Non-Contiguous Process
Jun 19, 2026Hail Hochman, Natalie Shapira, Yoav GoldbergLLM Interpretability Factual Knowledge in Language Models
Bar-Ilan University · Northeastern University
Does RoPE Prevent or Degrade Retrieval Heads? A Mechanistic Analysis Across Model Families
Jun 19, 2026Cengizhan BayramRotary Positional Embeddings Long-Context Retrieval
Independent Researcher
A Multi-Agent Audit Framework for High-Stakes Reasoning: Evaluation and Interpretability in Clinical Mental Health Screening
Jun 19, 2026Jingchen Ye, Yanpei Yu, Luyao ZhangLLM Auditing LLM Interpretability
Duke Kunshan University Suzhou, China · Social Science Division and Digital Innovation Research Center, Duke Kunshan University, No.8 Duke Ave., Kunshan, Jiangsu 215316, China.
A Validation-Gated Mechanistic Account of Suicidality Detection in LLMs
Jun 19, 2026Nafiz Ahmed, Sarah Sharif, Dingjing Shi +1LLM Interpretability Mental Health
Intelligent Neuromorphic and Quantum Understanding for Innovative Research and Engineering (INQUIRE) Lab, School of Electrical and Computer Engineering, University of Oklahoma, Norman, 73019, Oklahoma, U.S.A. · School of Psychology, Georgia Institute of Technology, Atlanta, 30332, Georgia, U.S.A.
What Shapes Emergent Misalignment? Insights from Training Dynamics, Model Priors, and Data
Jun 18, 2026Yuchen Zhang, Anietta Weckauff, Diego Garcia-Olano +1LLM Evaluation LLM Alignment
Max Planck Institute for Intelligent Systems, ELLIS Institute Tübingen, Tübingen AI Center, Tübingen, Germany · Meta.
How Transparent is DiffusionGemma?
Jun 18, 2026Joshua Engels, Callum McDougall, Bilal Chughtai +11LLM Interpretability Diffusion Language Models
Google DeepMind
From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models
Jun 18, 2026Jiaxu Zuo, Mu You, Kaixin Lan +5LLM Interpretability Automated Essay Scoring
NLP2CT Lab, Department of Computer and Information Science, University of Macau · Institute of International Language Services Studies, Macau Millennium College · School of Data Science and Information Engineering, Guizhou Minzu University
Explaining Attention with Program Synthesis
Jun 17, 2026Amiri Hayes, Belinda Z Li, Jacob AndreasTransformer Interpretability Attention Head Analysis
NJIT · MIT EECS
LLM Parameters for Math Across Languages: Shared or Separate?
Jun 16, 2026Behzad Shomali, Luisa Victor, Tim Selbach +5Multilingual Language Models Cross-Lingual Reasoning in Language Models
Lamarr Institute · University of Bonn · Fraunhofer IAIS
From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability
Jun 16, 2026Dibyanayan Bandyopadhyay, Asif EkbalLLM Interpretability Sparse Autoencoders
Department of Computer Science and Engineering, Indian Institute of Technology Patna, Bihar, India.
Self-CTRL: Self-Consistency Training with Reinforcement Learning
Jun 16, 2026Itamar Pres, Laura Ruis, Melat Ghebreselassie +2RL for Language Models Faithfulness of Language Model Explanations
MIT CSAIL
From Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMs
Jun 16, 2026Siyue Chen, Yifu Guo, Yuquan Lu +9LLM Interpretability Code Language Models
1South China University of Technology · 2Sun Yat-sen University · 4Shanghai Jiao Tong University +5
Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing
Jun 16, 2026Kexin Chen, Yi Liu, Haonan Zhang +3LLM Auditing LLM Interpretability
Zhejiang University · Griffith University
Rift: A Conflict Signature for Deception in Language Models
Jun 15, 2026Petr NyomaKnowledge Conflicts in Language Models LLM Interpretability
Harmonic Labs
Scalable Circuit Learning for Interpreting Large Language Models
Jun 15, 2026Naiyu Yin, Dennis Wei, Tian Gao +3Circuit Discovery LLM Interpretability
Lehigh University, Mathematics Department, Bethlehem, USA · IBM Research, Yorktown Heights, USA.
Demystifying Variance in Circuit Discovery of LLMs
Jun 15, 2026Frank Zhengqing Wu, Francesco Tonin, Volkan CevherPrompt Sensitivity Circuit Discovery
Laboratory for Information and Inference Systems (LIONS) École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland · Laboratory for Informationand Inference Systems (LIONS) École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
A Mechanistic Understanding of Pronoun Fidelity in LLMs
Jun 15, 2026Katharina Trinley, Jesujoba O. Alabi, Dietrich Klakow +1Social Bias in Language Models LLM Interpretability
Saarland University, Germany · Heidelberg Institute for Theoretical Studies, Germany
Neuron Level Analysis of Large Language Model in Legal Domain Reasoning
Jun 14, 2026Eri Onami, Youmi Ma, Shuhei Kurita +1Legal NLP LLM Interpretability
Institute of Science Tokyo · NII · AIST
The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages
Jun 14, 2026Miso Choi, Seonga Choi, Mincheol Kwon +3LLM Grounding LLM Interpretability
Korea University, Seoul, Republic of Korea · Kakao Mobility Corp., Seongnam, Republic of Korea
Vernier: Probing Representational Misalignment Behind Lexical Gaps in Causal Reasoning
Jun 14, 2026Zhenyu YuLLM Interpretability Causal Reasoning in Language Models
College of Computer Science and Artificial Intelligence Fudan University
Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning
Jun 13, 2026Ali Dasdan, Manan Shah, W. Russell Neuman +3LLM Alignment Moral Reasoning in Language Models
1KD Consulting, CA, USA · 2New York University, NY, USA

Jun 21, 2026, cs.AIJ/K move · Enter open · S save

Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations

Dongyub Jude Lee, Jungseob Lee, Seungyoon Lee, Seongtae Hong+4

Zoom Communications · Korea University · Yonsei University+1

LLM Interpretability LLM Fine-Tuning LLM Safety Alignment LLM Safety Refusal Behavior in Language Models

Open paper AskPDF arXiv

Refusal on a safety benchmark does not reveal how stable that behavior will remain after model updates. Benign downstream fine-tuning can weaken refusal, yet behavioral evaluations typically expose this fragility only after an intervention. We introduce SKIN-DEEP, a geometric diagnostic that examines the unmodified model's residual-stream activations. It compares aligned and base checkpoints to identify safety-separating directions, tests their behavioral relevance through ablation, and summarizes the layer-wise pattern in the Geometric Fragility Score (GFS). Across twenty-one instruction-tuned models, harmful requests and benign instructions exhibit a recurring low-rank separation pattern. Selected direction ablations weaken refusal, with the effective direction varying across models. In benign low-rank fine-tuning experiments, the initially safe model with the lowest score before fine-tuning has the lowest harmful-compliance rate when trained on the largest tested set of harmless examples. These findings connect representation geometry to subsequent behavioral susceptibility and support activation-based diagnostics as a complement to refusal tests. Our code is available at https://github.com/js-lee-AI/skin-deep.

Momentum

Related topics

Latest papers 546