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

From Plausible to Actionable: A Position on LLM Self-Explanations
Jul 17, 2026Elize Herrewijnen, Benedetta Muscato, Gizem Gezici +1CoT Faithfulness Faithfulness of Language Model Explanations
University of Utrecht, Utrecht, Netherlands · National Police Lab AI, Netherlands Police, Driebergen, Netherlands · Scuola Normale Superiore, Pisa, Italy +1
Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions
Jul 15, 2026Zachary IzzoLanguage Model Pretraining Transformer Interpretability
NEC Labs America
AIMO Interpretability Challenge
Jul 15, 2026Michal Štefánik, Philipp Mondorf, Andreas Waldis +11Mathematical Reasoning Benchmarks LLM Interpretability
National Institute of Informatics, Japan · Munich Center for Machine Learning / MaiNLP LMU · University of Tübingen +6
What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors
Jul 14, 2026Winston Zeng, Ali Emami, Jinho ChoiLanguage Model Steering LLM Interpretability
Emory University
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
Jul 13, 2026Zixiang Xu, Sixian Li, Huaxing Liu +4LLM-as-a-Judge LLM Interpretability
AMAP, Alibaba Group · Mohamed bin Zayed University of Artificial Intelligence · University of Southern California +1
Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs
Jul 12, 2026Shrestha Datta, Hongfu Liu, Anshuman ChhabraGradient-Based Attribution LLM Interpretability
University of South Florida, Tampa, FL, USA · Brandeis University, Waltham, MA, USA
Laguerre Geometry for Interpreting Large Language Models
Jul 12, 2026Chunwei Ma, Russell WolfingerTransformer Interpretability LLM Interpretability
JMP Statistical Discovery, Cary, NC, USA
SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models
Jul 11, 2026Dongxu Zhang, Yiding Sun, Zihao Guo +5LLM Interpretability Activation Steering
Xi’an Jiaotong University · Peking University · Tencent
Belief-reality separation lives in routing over a shared value slot in language models
Jul 11, 2026Oliver Steele, Jiangtao Wen, Yuxing HanTheory of Mind LLM Interpretability
Tsinghua University · NYU Shanghai
One mechanism for many mental spaces: a shared router over a value slot in language models
Jul 11, 2026Oliver Steele, Jiangtao Wen, Yuxing HanLLM Interpretability Circuits in Language Models
Tsinghua University · NYU Shanghai
All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models
Jul 10, 2026Pan LiExplainable Artificial Intelligence LLM Interpretability
Scheller College of Business, Georgia Tech.
TypeProbe: Recovering Type Representations from Hidden States of Pre-trained Code Models
Jul 9, 2026Giuliano Gorgone, Fausto CarcassiLLM Interpretability Representation Geometry in Language Models
ILLC, University of Amsterdam, Amsterdam, The Netherlands
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
Jul 8, 2026Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang +1LLM Interpretability Adversarial Attacks on LLMs
Department of Computer Science, University of South Dakota, USA · School of Information and Artificial Intelligence, Yangzhou University, Yangzhou, China
Distributed Sparse Interventions in Language Models
Jul 8, 2026Maximilian S. Ernst, Lorenz Linhardt, Aaron Peikert +1Language Model Steering LLM Interpretability
Max Planck School of Cognition · Center for Lifespan Psychology Max Planck Institute for Human Development · Machine Learning Group Technische Universität Berlin +5
Dissociating the Internal Representations of Sycophancy in LLMs
Jul 8, 2026Anthony Baez, Sheer Karny, Pat PataranutapornLLM Sycophancy LLM Interpretability
Media Lab, MIT, Massachusetts, USA.
Reward Valuation in Large Language Models: Causal Induction of Anhedonia
Jul 7, 2026Melika Honarmand, Samin Mahdipour Aghabagher, Martin SchrimpfReward Modeling Cognitive Modeling
NeuroAI Laboratory, EPFL
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
Jul 6, 2026Mohamed Amine Merzouk, Dmitri Carpov, Mirko Bronzi +2LLM Interpretability
Mila, Quebec AI Institute · McGill University · LawZero
Latent Programming Horizons in Coding Agents
Jul 6, 2026André Silva, Han Tu, Martin MonperrusLLM Interpretability Coding Agents
KTH Royal Institute of Technology Stockholm, Sweden
Wrong Before Right: Late Rescue and Interface Failure in Aligned Language Models
Jul 6, 2026Jiaqi DengLLM Alignment LLM Interpretability
Independent Researcher
Unsupervised Features Mining via Activation Geometry
Jul 5, 2026Amit LeVi, Elad David, Max FominLLM Interpretability Unsupervised Representation Learning
Zenity Tel Aviv, Israel
Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs
Jul 4, 2026Kareem Elozeiri, Mervat Abassy, Omar Kallas +4Arabic NLP LLM Interpretability
1Mohamed bin Zayed University of Artificial Intelligence · 2Qatar Computing Research Institute, Hamad Bin Khalifa University · 3Tohoku University +1
Reading Between the Dots: Decoding Hidden Computation across Filler Tokens
Jul 3, 2026Kaley Brauer, Claudio Mayrink Verdun, Samuel MarksLLM Auditing LLM Interpretability
Harvard University · 4Anthropic
Fast Multi-dimensional Refusal Subspaces via RFM-AGOP
Jul 2, 2026Thomas WinningerLLM Interpretability LLM Safety
Télécom SudParis, Évry-Courcouronnes, France · ENS Paris-Saclay, Gif-sur-Yvette, France
Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates
Jul 1, 2026Elias Najarro, Ane Espeseth, Eleni Nisioti +2Artificial Life LLM Interpretability
IT University of Copenhagen, Denmark · University of Oslo, Norway · Sakana AI, Japan +1
Understanding Large Language Models
Jul 1, 2026Yannik Keller, Thomas EisenmannLLM Interpretability
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
Jul 1, 2026Aryo Pradipta Gema, Beatrice Alex, Pasquale MinerviniLong-Context Retrieval Attention Head Analysis
QUniversity of Edinburgh · KHeriot-Watt University · V Miniml.AI
Shapley in Context: Explaining Financial Language with Domain Expertise
Jul 1, 2026Dangxing Chen, Pengzhan GuoLLM Interpretability Shapley Value Attribution
Zu Chongzhi Center, Duke Kunshan University, Kunshan, Jiangsu, CN · Digital Innovation Research Center, Duke Kunshan University, Kunshan, Jiangsu, CN
Prototype Language Models
Jul 1, 2026Dan Ley, Giang Nguyen, Himabindu Lakkaraju +1LLM Interpretability Language Modeling
1Harvard University · 2Guide Labs Inc. *Work initiated during an internship at Guide Labs. · 2Guide Labs Inc.
A Mechanistic View of Authority Hierarchy in LLM Sycophancy
Jul 1, 2026Emil Joswin, Srujananjali Medicherla, Priyanka Mary MammenLLM Sycophancy LLM Interpretability
Independent Research · University of Massachusetts Amherst
NeuroCogMap Reveals Cognitive Organization of Large Language Models
Jul 1, 2026Zhongxiang Sun, Haolang Lu, Qiang Ma +11Cognitive Modeling LLM Interpretability
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · Beijing University of Posts and Telecommunications, Beijing, China · The University of Hong Kong, Hong Kong, China +5

Jul 17, 2026, cs.CLJ/K move · Enter open · S save

From Plausible to Actionable: A Position on LLM Self-Explanations

Elize Herrewijnen, Benedetta Muscato, Gizem Gezici, Fosca Giannotti

University of Utrecht, Utrecht, Netherlands · National Police Lab AI, Netherlands Police, Driebergen, Netherlands · Scuola Normale Superiore, Pisa, Italy+1

CoT Faithfulness Faithfulness of Language Model Explanations LLM Interpretability Explainability Evaluation

Open paper AskPDF arXiv

Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations. Such explanations have emerged as a promising direction for explainable artificial intelligence (XAI), particularly for interpreting LLM behavior. However, while self-explanations often appear plausible, whether they faithfully reflect a model's underlying reasoning process remains an open question. In this opinion paper, we argue that self-explanations can be highly plausible, questionably faithful, and yet highly actionable. From a traditional XAI perspective, we identify the limitations of standard evaluation protocols for LLM-generated self-explanations and propose practical guidelines for assessing their plausibility and faithfulness. Moreover, we argue that evaluation should extend beyond these criteria to actionability, highlighting applications of LLM rationalization capabilities that support informed decision-making and appropriate action across diverse stakeholders.

Momentum

Related topics

Latest papers 546