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

Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs
May 7, 2026Fahd Seddik, Fatemeh FardLLM Evaluation LLM Interpretability
Department of Computer Science University of British Columbia Kelowna, BC, Canada
Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals
May 6, 2026Gijs van DijkLanguage Model Error Detection Confidence Estimation in Language Models
Utrecht University
A geometric relation of the error introduced by sampling a language model's output distribution to its internal state
May 6, 2026Albert F. ModenbachNeural Representation Geometry LLM Interpretability
Department of Mathematics, King’s College London, United Kingdom.
Gyan: An Explainable Neuro-Symbolic Language Model
May 6, 2026Venkat Srinivasan, Vishaal Jatav, Anushka Chandrababu +1LLM Interpretability Knowledge Representation
Innospark Ventures & Gyan AI · Gyan AI Inc.
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
May 5, 2026Qingzhuo Wang, Ruiyang Qin, Zhenxin Qin +2Feature Interaction Modeling LLM Interpretability
School of Computer Science and Technology, Tongji University, Shanghai, China.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
May 4, 2026Yash Aggarwal, Atmika Gorti, Vinija Jain +3Moral Reasoning in Language Models Social Bias in Language Models
University of Maryland, College Park · 2Purdue University · 3Meta +5
Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation
May 4, 2026Francesco Sovrano, Gabriele Dominici, Marc LangheinrichLLM Interpretability Mechanistic Interpretability
Università della Svizzera italiana Lugano, Switzerland
How Language Models Process Negation
May 4, 2026Zhejian Zhou, Tianyi Zhou, Robin Jia +1LLM Interpretability Language Modeling
Information Sciences Institute, University of Southern California · Thomas Lord Department of Computer Science, University of Southern California
So Many Opinions, So Many LLMs: Comparing Large Language Models to Traditional Machine Learning for Open- Ended Survey Analysis
May 4, 2026Abdullah Akinde, Mariam Akinde, Rasheedat Emiola +1LLM Evaluation LLM Interpretability
Austin Peay State University, United States
The Dynamic Gist-Based Memory Model (DGMM): A Memory-Centric Architecture for Artificial Intelligence
May 4, 2026Terry Dorsey, Kevin HugginsMemory-Augmented Neural Networks LLM Interpretability
Harrisburg University of Science and Technology, USA
Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs
May 3, 2026HarshavardhanLLM Interpretability Sparse Autoencoders
Independent Researcher
Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models
May 3, 2026Kotaro Furuya, Takahito TanimuraTransformer Interpretability LLM Evaluation
Research and Development Group, Hitachi, Ltd. 1-280 Higashi-Koigakubo, Kokubunji-shi, Tokyo 185-8601, Japan
The Cylindrical Representation Hypothesis for Language Model Steering
May 3, 2026Lang Gao, Jinghui Zhang, Wei Liu +7Language Model Steering LLM Interpretability
Department of Natural Language Processing, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · Department of Computer Science, National University of Singapore, Singapore
Reasoning emerges from constrained inference manifolds in large language models
May 2, 2026Yanbiao Ma, Fei Luo, Linfeng Zhang +10LLM Inference LLM Interpretability
Renmin University of China · Tsinghua University · Xiaomi EV +1
Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
May 1, 2026Sheridan Feucht, Tal Haklay, Usha Bhalla +9Numerical Reasoning in Language Models LLM Interpretability
aNortheastern University · bTechnion IIT · cHarvard University +1
Persona Without Substrate: Regime-Dependence and the LLM Individuation Problem
May 1, 2026Shuaizhi ChengLLM Interpretability Personality Modeling in Language Models
Harbin Institute of Technology
How Language Models Process Out-of-Distribution Inputs: A Two-Pathway Framework
Apr 30, 2026Hamidreza SaghirLLM Interpretability Attention Mechanisms
Independent Researcher
Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions
Apr 30, 2026Jan Sobotka, Mustafa O. Karabag, Ufuk TopcuImperfect-Information Games LLM Interpretability
EPFL · The University of Texas at Austin
Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models
Apr 30, 2026Shubham Kumar, Narendra AhujaLLM Interpretability Causal Reasoning in Language Models
University of Illinois Urbana-Champaign
DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models
Apr 30, 2026Lifan Zheng, Xue Yang, Jiawei Chen +6LLM Interpretability Personality Modeling in Language Models
Southeast University · Shanghai Jiao Tong University · East China Normal University +6
Modeling Clinical Concern Trajectories in Language Model Agents
Apr 30, 2026Sukesh Subaharan, Venkatesan VS, Murugadasan P +3LLM Interpretability AI Agent Monitoring
Coimbatore Medical College · Coimbatore, TN · India
TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models
Apr 30, 2026Amirreza Esmaeili, Fatemeh FardLLM Interpretability Code Generation
University of British Columbia Kelowna, British Columbia, Canada
Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs
Apr 30, 2026Hongliang Liu, Tung-Ling Li, Yuhao WuLLM Interpretability Mechanistic Interpretability
Palo Alto Networks
Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models
Apr 29, 2026Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter +3LLM Interpretability Instruction Following
School of Computer Science, University of Sheffield · School of EECS, Queen Mary University of London · The Alan Turing Institute
Semantic Structure of Feature Space in Large Language Models
Apr 29, 2026Austin C. Kozlowski, Andrei BoutylineNeural Representation Geometry LLM Interpretability
Knowledge Lab · University of Chicago · Department of Sociology +1
What Suppresses Nash Equilibrium Play in Large Language Models? Mechanistic Evidence and Causal Control
Apr 29, 2026Paraskevas V. Lekeas, Giorgos StamatopoulosNash Equilibrium Game Theory
DreamWorks Animation, Glendale, USA · Department of Economics, University of Crete2026 Rethymno, Crete, Greece
MoRFI: Monotonic Sparse Autoencoder Feature Identification
Apr 29, 2026Dimitris Dimakopoulos, Shay B. Cohen, Ioannis KonstasLLM Hallucination Mitigation LLM Interpretability
University of Edinburgh, UK · Heriot-Watt University, UK
Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens
Apr 29, 2026Zhenyu Zhao, Sander Land, Daniel M. Bikel +1LLM Compression LLM Interpretability
Writer, Inc.
reward-lens: A Mechanistic Interpretability Library for Reward Models
Apr 28, 2026Mohammed Suhail B NadafReward Modeling LLM Interpretability
Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders
Apr 28, 2026Bangzhao Shu, Arinjay Singh, Mai ElSheriefLLM Interpretability Causal Interventions in Language Models
Northeastern University

May 7, 2026, cs.CLJ/K move · Enter open · S save

Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs

Fahd Seddik, Fatemeh Fard

Department of Computer Science University of British Columbia Kelowna, BC, Canada

LLM Evaluation LLM Interpretability LLM Reasoning

Open paper AskPDF arXiv

We introduce an axiomatic evaluation framework for latent thought representations in LLMs, comprising metrics that are independent of downstream benchmark scores and reveal representational failures that benchmark accuracy masks. Existing evaluations conflate representation quality with model capacity. Therefore, failures cannot be attributed to the representation rather than to the model that processes it. We formalize four functional axioms (Causality, Minimality, Separability, and Stability) and define a quantitative measure for each, computed directly on the representation independently of downstream accuracy. We audit open-weight LLMs across 23 reasoning tasks (e.g., Spatial Reasoning, Factual QA). We find that no candidate satisfies all four axioms simultaneously, that the representations distinguish task type reliably but cannot distinguish between two questions within the same task, and that the representations encode little information beyond what is already present in the input embedding. The failure is consistent across dense, reasoning-distilled, and RL-trained model families, indicating that the gap is structural rather than a property of model size or training procedure.

Momentum

Related topics

Latest papers 546