Language Model Probing

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, up 12% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 192

All topics

Investigating Assistant Bias in LLM User Simulators Using a Role Vector
Sep 1, 2026Daeheon Jeong, Yoonjoo Lee, Eugene Choi +2Large Language Model-Based Role-Play Simulation User Simulation
1KAIST · University of Michigan · 3Seoul National University +2
Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs
Aug 31, 2026Deniz Bayazit, Badr AlKhamissi, Antoine BosselutMultilingual Language Models Multilingual Language Model Evaluation
EPFL
BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
Aug 31, 2026Adrians Skapars, Edoardo ManinoLanguage Model Steering Language Model Safety Evaluation
University of Manchester, United Kingdom
Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores
Aug 31, 2026Qiyao Yan, Chenpeng Wang, Liangming PanLLM Evaluation Language Model Calibration
State Key Laboratory of Multimedia Information Processing, Peking University · School of Computer Science, Peking University · YiXin-AILab, YIXIN, Beijing, China +1
Answer Probing-Guided Search for Diverse Solution Exploration of LLMs
Aug 31, 2026Yi Fang, Que Shen, Chengpeng Li +6Language Model Probing LLM Reasoning
University of Science and Technology of China · Zhongguancun Academy · Alibaba Group +2
Small Language Models as Judges for Rubric-Based Reinforcement Learning
Aug 30, 2026Fengyu Xie, Yilun Zhao, Bingsen Chen +2LLM-as-a-Judge Language Model Generation Evaluation
New York University · Yale University
Detecting Hidden Chain-of-Thought in Large Language Models with Linguistic, Behavioral, and Mechanistic Indicators
Aug 30, 2026Armaan Singh, Ryan Trinh Le, Jasmine Kaur +5LLM Evaluation LLM Interpretability
1Stanford University · 2York University · 3Facebook
Sleight of Word Benchmark: Can Language Models Notice If Their Own Output Was Tampered With?
Aug 30, 2026Alberto CetoliLanguage Model Generation Evaluation Language Model Self-Assessment
Cleo
A Probe Direction Is a Property of Its Prompt
Aug 13, 2026Valentin NoëlPrompt Sensitivity LLM Evaluation
Devoteam
Memorization Diagnostics for Code LLMs Should be Scale-Aware
Aug 13, 2026Prateek Kumar Rajput, Abdoul Aziz Bonkoungou, Alberick Euraste Djiré +6Memorization in Language Models Code Language Models
University of Luxembourg, Esch-sur-Alzette, Luxembourg.
Task- and dataset-specific information in protein language models
Aug 12, 2026Roman Joeres, Ilya Senatorov, Anastasia Kolchina +2Protein Language Models Protein Representation Learning
Drug Bioinformatics, Helmholtz Institute for Pharmaceutical Research Saarland, 66123 Saarbruecken, Germany · Center for Bioinformatics, Saarland University, 66123 Saarbruecken, Germany · Saarland Informatics Campus, Saarland University, 66123 Saarbruecken, Germany +2
What Iterated Self-Feeding Probes of Language Models Measure, and a test that separates the construction from the model
Aug 11, 2026Nicolás Vera ZúñigaLanguage Model Probing
Independent Researcher, Chile
Activation Probes Surface Code-Security Signals that the Model's Output Misses
Aug 10, 2026Ivan WiryadiLLM Auditing Software Vulnerability Detection
Independent.
One Adapter Pair per Model: A Universal Activation Interface for Language Models
Aug 10, 2026Su-Hyeon Kim, Jiwan Mun, Yo-Sub HanRepresentation Geometry in Language Models Language Model Probing
Department of Artificial Intelligence, Yonsei University · Department of Computer Science, Yonsei University
On the Robustness of LLMs' Internal Representation of Code Correctness
Aug 8, 2026Francisco Ribeiro, Sohaila Abdulsattar, Renata Gonzalez +2LLM Reliability Language Model Robustness
New York University Abu Dhabi Abu Dhabi, United Arab Emirates
Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families
Aug 8, 2026Alizishaan Khatri, Dun Li ChanLLM Safety Benchmarks LLM Inference
Wrynx Inc · INTI International College Penang
Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States
Aug 8, 2026Zakhar Mrykhin, Valentin MalykhLLM Hallucination Detection Language Model Probing
HSE University
"Many Are My Names": The Anatomy of the Assistant and Its Personas via Sparse Autoencoders
Aug 8, 2026Adelaide Danilov, Aria Nourbakhsh, Oleksandr Marchenko Breneur +1Large Language Model-Based Role-Play Simulation Personality Modeling in Language Models
Department of Computer Science, Faculty of Science, Technology and Medicine, University of Luxembourg
Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding
Aug 7, 2026Karim Radouane, Jose G Moreno, Lynda TamineSpatial Reasoning Benchmarks LLM Grounding
University of Toulouse, IRIT Toulouse, France
Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes
Aug 7, 2026Luc Hazenoot, Zhaochun Ren, Amirhossein ZohrehvandLinear Probing LLM Interpretability
Leiden Institute of Advanced Computer Science, Leiden University
Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools
Aug 5, 2026Atul Anand, Sourav ChattarajLLM Agent Evaluation Tool-Using Language Agents
STRIVE: Probing Reasoning Limits in Graded Plausibility Generation and Evaluation
Aug 5, 2026Bhiman Kumar Baghel, Anna Chrabaszcz, Tessa Warren +3LLM Evaluation Controllable Text Generation
University of Pittsburgh, Pittsburgh, PA, USA · University of Wisconsin–Madison, Madison, WI, USA
Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive Inference
Aug 4, 2026Shahrukh Mohiuddin, Chalamalasetti Kranti, Sherzod Hakimov +1LLM Evaluation Language Model Probing
Computational Linguistics, Department of Linguistics University of Potsdam, Germany · German Research Center for Artificial Intelligence (DFKI), Berlin, Germany
Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains
Aug 4, 2026Yanchao Li, Wanhao Liu, Jiaqing Xie +4LLM Evaluation LLM Auditing
Nanjing University · Shanghai Artificial Intelligence Laboratory · North University of China
ChaosProbe: A Neurochaotic Lens on Frozen Transformer Input-Embedding Spaces
Aug 3, 2026Kunal Kumar Pant, Nithin NagarajLanguage Model Fingerprinting Representation Probing
Department of Electronics and Communication Engineering (ECE) Amrita Vishwa Vidyapeetham Kollam, Kerala, India · Complex Systems Programme National Institute of Advanced Studies (NIAS) IISc Campus, Bengaluru Karnataka, India
BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning
Jul 31, 2026Keshu Fu, Keqin Peng, Jun Bai +6Efficient Language Model Reasoning Efficient Language Model Inference
School of Computer Science and Engineering, Beihang University · Beijing Institute for General Artificial Intelligence, BIGAI · Academy for Advanced Interdisciplinary Studies, Peking University +1
RepBench: Compiling Benchmarks into Capability Representations for Large Language Models
Jul 30, 2026Yanshi Li, Xueru Bai, Shuman Liu +1LLM Evaluation LLM Interpretability
Shopee, Shanghai, China · Shopee, Beijing, China
Sky sphere representation in language models
Jul 29, 2026Aleksandr Berdnikov, Yevgeny LiokumovichFactual Knowledge in Language Models Representation Geometry in Language Models
Fields Institute · Principles of Intelligence · University of Toronto
Stemma: Induced Decision Regions Reveal LLM Provenance
Jul 28, 2026Keyu Zhang, Vadim Safronov, Andrew MartinLanguage Model Fingerprinting Language Model Probing
Department of Computer Science, University of Oxford
Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study
Jul 24, 2026Luis Espinosa-Anke, Carla Perez-AlmendrosLLM Safety Representation Geometry in Language Models
Cardiff University

Sep 1, 2026, cs.CLJ/K move · Enter open · S save

Investigating Assistant Bias in LLM User Simulators Using a Role Vector

Daeheon Jeong, Yoonjoo Lee, Eugene Choi, Sinie van der Ben+1

1KAIST · University of Michigan · 3Seoul National University+2

Large Language Model-Based Role-Play Simulation User Simulation Activation Steering Language Model Probing

Open paper AskPDF arXiv

LLM-based user simulators are increasingly used to evaluate autonomous agents at scale, in place of costly human evaluations. Despite this promise, these simulators exhibit "assistant bias," a tendency to cooperate and pursue task goals. They rarely reproduce the frustration or disengagement that real users exhibit, compromising evaluation validity. Prior work outlines that this bias is baked in during model training, which role-playing prompts fail to override. We analyze this bias from model activations, extracting a user role vector by contrasting how the model represents user versus assistant perspectives on the same dialogue. We observe two findings: (i) the user direction is identifiable in activations, elicits user-like behaviors, and captures characteristics distinct from assistant traits; and (ii) although user-role activation associates with simulation realism and steering strengthens it, it can exaggerate user behaviors and override individual user profiles. Together, our findings provide a representation-level analysis of LLM user simulators, confirming that assistant bias is structurally identifiable and that user behavior can be directionally analyzed.

Momentum

Related topics

Latest papers 192