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

Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance
Oct 8, 2026Zheng Huang, Sansheng Cao, Enpei Zhang +7LLM Reasoning LLM Interpretability
Dartmouth College · Yale University · New York University +2
SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models
Oct 7, 2026Miao Yu, Hao Huang, Lu Yuan +3LLM Safety Alignment LLM Alignment
The University of Hong Kong (HKU) · Chinese Academy of Sciences (CAS) · Information Engineering University (IEU) +1
How Do LLMs Change Predictions Under Negation?
Oct 7, 2026Jongwook Yoon, Jongwon Lim, Sungjib Lim +2LLM Reliability LLM Evaluation
Graduate School of Data Science, Seoul National University · Department of Computer Science and Engineering, Seoul National University
The Attribution Blind Spot: Layerwise Trajectory Diagnostics for Source Reliance in Retrieval-Augmented Language Models
Oct 7, 2026Zhe Yu, Wenpeng Xing, Yunzhao Wei +4LLM Interpretability Retrieval-Augmented Generation
Zhejiang University · Binjiang Institute of Zhejiang University · East China Normal University +3
U-Space: Uncovering When and Why Uncertainty Arises in Language Models
Oct 6, 2026Tobias Braun, Nils Loose, Alexander Herzog +4LLM Uncertainty Estimation Confidence Estimation in Language Models
Technische Universität Darmstadt · University College London · Universität zu Lübeck +2
Latent space bias directions in LLMs capture confidence, not fairness
Oct 6, 2026Stephanie Buttigieg, Maeve Madigan, Parameswaran Kamalaruban +1Debiased ML Language Model Steering
Institute of Astronomy & Kavli Institute for Cosmology, University of Cambridge, UK · Risk and Security AI Lab, Visa Inc., Cambridge, UK
Finding the Heads and the Neurons Responsible for Network Information Retrieval in Language Models
Oct 6, 2026Md Abdul Kadir, Md Mohasin Hossain, Daniel SonntagAttention Head Analysis LLM Interpretability
University of Oldenburg, Oldenburg, Germany · German Research Center for Artificial Intelligence · Saarland University, Saarbrucken, Germany
Do LLMs Act on What They Know? From Partner Representations to Cooperative Actions
Oct 6, 2026Yuhwan Jeong, Jinnyeong Yang, Kuk-Jin YoonMulti-Agent LLM Systems LLM Interpretability
KAIST, Visual Intelligence Lab
COMPASS: Finding Where Reasoning Lives in Language Models
Oct 5, 2026Pratyay Dutta, Kowshik Thopalli, Vivek NarayanaswamyEfficient Language Model Reasoning Activation Steering
University of California, Riverside, CA 92521. Work performed during a summer internship at Lawrence Livermore National Laboratory · Lawrence Livermore National Laboratory, Livermore, CA 94550.
Identifying Introspection From the Inside
Oct 5, 2026David I. Atkinson, Dillon Plunkett, David BauLLM Interpretability Language Model Introspection
Northeastern University · Eleos AI Research
Before Agent Tells The Lie: Has Deception Already Been Represented?
Oct 5, 2026Xinling Li, Dadi Guo, Qingyu Liu +5LLM Interpretability Deception in Language Models
South China University of Technology · The Hong Kong University of Science and Technology · Shanghai Artificial Intelligence Laboratory +1
Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models
Oct 1, 2026Tido Specht, Elias Benedict Krey, Nils Neukirch +1LLM Alignment LLM Interpretability
University of Groningen · Carl von Ossietzky University of Oldenburg
Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models
Oct 1, 2026Darpan Aswal, Céline HudelotIntegrated Gradients LLM Interpretability
Université Grenoble Alpes · MICS, CentraleSupélec
Persistent Depth Ordering amid Shifting Block-Bypass Responses in Language Model Pretraining
Oct 1, 2026Shengye Tao, Yinzhu Cheng, Haihua XieLLM Interpretability Causal Interventions in Language Models
Beijing University of Civil Engineering and Architecture · Beijing Institute of Mathematical Sciences and Applications (BIMSA) · Institute of Statistics and Big Data, Renmin University of China
Lingtai: What Concept Geometry Reveals--and Does Not Reveal--About LLM Inference
Sep 30, 2026Jiangang ChenLLM Inference LLM Interpretability
Chengdu Beiluoshimen Technology Co., Ltd.
Interpreting Reasoning of Large Language Models via Partial Information Decomposition
Sep 30, 2026Barproda Halder, Qiuyi Zhang, Sanghamitra DuttaLLM Interpretability Efficient Language Model Reasoning
University of Maryland, College Park · Elorian AI
Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment
Sep 30, 2026Yihuai Hong, Shauli Ravfogel, Chen Zhao +1CoT Faithfulness Faithfulness of Language Model Explanations
New York University · NYU Shanghai
Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting
Sep 30, 2026Liang Twist Shan, Tianyu Hu, Hao Yan +1Numerical Reasoning in Language Models Long-Context Retrieval
Department of Statistics, University of Wisconsin-Madison · Department of Computer Sciences, University of Wisconsin-Madison
Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability
Sep 29, 2026Zhenting Huang, Bo Jiang, Junnan Liu +2Activation Sparsity LLM Interpretability
Beihang University · Monash University · Zhongguancun Laboratory
XU-RS: Explaining Credal Width in Random-Set Language Models
Sep 29, 2026David Achara, Maryam Sultana, Alexander D. Rast +1LLM Interpretability LLM Uncertainty Estimation
Institute for AI, Data Analysis and Systems (AIDAS) Oxford Brookes University
In-Context Learning Amplifies a Latent Symbolic Circuit
Sep 28, 2026Melissa WesselLLM Interpretability In-Context Learning
Independent Researcher.
A Polyphonic Conception of AI Understanding
Sep 28, 2026Matthieu Queloz, Pierre BeckmannLLM Interpretability LLM Reliability
University of Bern, Department of Philosophy · École Polytechnique Fédérale de Lausanne (EPFL) · Idiap Research Institute +1
Causal and Interpretable Structures in LLM Compositional Tasks
Sep 28, 2026Gurbir Arora, Toni J. B. Liu, Jiajun Bao +2LLM Interpretability Causal Interventions in Language Models
Cornell University, USA · Goodfire AI, USA
Late Attention Layers Alone Can Copy Entity Tokens, but Not Without Attending to Their Context
Sep 28, 2026Muyu He, Yuchen Liu, Ran Tao +1Memorization in Language Models LLM Interpretability
Independent · University of Pennsylvania · Drexel University
Not All Thinking is Created Equal: Latent Reasoning Discovers a Recurrent Search Algorithm for Depth Generalization
Sep 28, 2026Huzi Cheng, Zhewei ZhangLLM Reasoning with Graphs LLM Interpretability
University of Minnesota · Independent Researcher
Signatures of semantic search in the activations of large language models
Sep 28, 2026Luke Leckie, Peter M. Todd, Jacob G. FosterExploration-Exploitation Tradeoff LLM Interpretability
Department of Informatics, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN · Cognitive Science Program, Indiana University, Bloomington, IN · Center for Possible Minds, Indiana University, Bloomington, IN +2
Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery
Sep 28, 2026Xu Wang, Yifan Yang, TingHao YU +1Representation Learning LLM Interpretability
The University of Hong Kong · Hunyuan Team, Tencent
Imprint Reader: From Weight-Update Readout to Behavioral Intervention
Sep 28, 2026Guanxu Chen, Qihao Lin, Jing ShaoLLM Interpretability Neural Network Interpretability
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University
A mechanistic study of language model introspection
Sep 28, 2026Jiahong Zou, Xiangkun Sun, Lingkai Kong +1Attention Head Analysis LLM Interpretability
Shandong University · Tsinghua University · Northeastern University +1
Echoes of Deeds: Moral History Can Shape and Steer LLM Behavioral Choices
Sep 28, 2026Lucio La Cava, Andrea TagarelliMoral Reasoning in Language Models LLM Auditing
DIMES Dept., University of Calabria, Italy

Oct 8, 2026, cs.AIJ/K move · Enter open · S save

Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance

Zheng Huang, Sansheng Cao, Enpei Zhang, Weikang Qiu+6

Dartmouth College · Yale University · New York University+2

LLM Reasoning LLM Interpretability LLM Pruning Attention Head Pruning

Open paper AskPDF arXiv

Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoning ability is reflected in internal organization. Inspired by neuroscience findings linking higher intelligence to stronger small-world organization in functional brain networks, we investigate small-world connectivity as a structural signature of LLM reasoning. We construct functional graphs from attention-head activation similarities and find that a higher small-world index (SWI), capturing local clustering and short global paths, consistently correlates with better fluid reasoning performance across models and training checkpoints. Since local clustering is central to small-world organization, we further examine how heads important for model performance connect within and across communities. We find that these heads tend to have a larger share of connection weight within their own communities (high core scores) and a more concentrated weight distribution across communities (low bridge scores). These observations motivate the hypothesis that high core and low bridge scores serve as structural indicators of head importance for reasoning capability. We validate this hypothesis through pruning, introducing Small-World Allocation (SWA), a hierarchical sparsity allocation method guided by these scores. Across six LLMs, SWA better preserves small-world organization and model performance than competing allocation strategies, reducing WikiText perplexity by up to 20%. Together, these findings identify small-world functional connectivity as a measurable signature of LLM reasoning performance, offering a structural perspective that complements behavioral evaluation.

Momentum

Related topics

Latest papers 546