Language Model Probing

Follow this topic Ask about this topic

Language model probing studies what models represent internally and what they can do, using controlled tasks to examine hidden activations, attention, logits, and generated behavior. Common approaches include training linear or nonlinear readouts on activations, comparing representations across layers and prompts, and testing causal effects with interventions such as activation patching or steering. Probes are used to investigate linguistic knowledge, reasoning, uncertainty, hallucination, safety, and model performance, and can support practical tools for monitoring, routing, and evaluation. A central open tension is that decodable information may not be used to produce an answer, while probe results can also reflect prompt structure, labels, or dataset artifacts rather than the intended capability.

Latest papers

280 papers35 papers in the last four weeks, up 35% on the four weeks before. 0.2% of all new papers.

BoRP: Bootstrapped Regression Probing for Scalable and Human-Aligned LLM Evaluation
Jan 26, 2026Peng Sun, Xiangyu Zhang, Duan Wu +5LLM Evaluation Representation Probing
Qwen Business Unit of Alibaba
LLMs Think with DAGs: Probing the Latent Graph Structure of Reasoning
Jan 24, 2026Tianjun Zhong, Linyang He, Ziyang Li +1Structured Reasoning in Language Models LLM Reasoning with Graphs
Columbia University · Johns Hopkins University
Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
Sep 29, 2025Marco Bronzini, Carlo Nicolini, Bruno Lepri +2LLM Interpretability Language Model Probing
Training-free Truthfulness Detection via Sparse MLP Value Vectors
Sep 22, 2025Runheng Liu, Heyan Huang, Xingchen Xiao +2LLM Reliability LLM Hallucination Detection
Beijing Institute of Technology Beijing, China
Human Psychometric Questionnaires Mischaracterize LLM Behavior
Sep 12, 2025Woojung Song, Dongmin Choi, Yoonah Park +3Personality Modeling in Language Models Psychometric Validation
1Graduate School of Data Science, Seoul National University · Department of Communication, Interdisciplinary Program in Artificial Intelligence, Seoul National University
Cross-Layer Attention Probing for Fine-Grained Hallucination Detection
Sep 4, 2025Malavika Suresh, Rahaf Aljundi, Ikechukwu Nkisi-Orji +1LLM Hallucination Detection LLM Reliability
Robert Gordon University, Aberdeen, United Kingdom · Toyota Motor Europe, Brussels, Belgium
The Trilemma of Truth in Large Language Models
Jun 30, 2025Germans Savcisens, Tina Eliassi-RadLLM Interpretability LLM Reliability
Khoury College of Computer Sciences Northeastern University, Boston, MA, USA · Network Science Institute Northeastern University, Boston, MA, USA · Santa Fe Institute, Santa Fe, NM, USA
Cross-Layer Discrete Concept Discovery for Interpreting Language Models
Jun 24, 2025Ankur Garg, Xuemin Yu, Hassan Sajjad +1Variational Autoencoders LLM Interpretability
Evaluating LLMs on Chinese Topic Constructions: A Research Proposal Inspired by Tian et al. (2024)
Apr 21, 2025Xiaodong YangLLM Evaluation Language Model Probing
College of Foreign Languages Zhejiang University of Technology 288, Liuhe Rd., Xihu District, Hangzhou, Zhejiang, 310023 China
Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models
Oct 3, 2024Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva +5Self-Attention Multiple-Choice Question Answering
Skolkovo Institute of Science and Technology · AI Foundation and Algorithm Lab · Moscow Institute of Physics and Technology +2

Jan 26, 2026J/K move · Enter open · S save

BoRP: Bootstrapped Regression Probing for Scalable and Human-Aligned LLM Evaluation

Peng Sun, Xiangyu Zhang, Duan Wu, Lu Tan+4

Qwen Business Unit of Alibaba

LLM Evaluation Representation Probing Automated Evaluation Language Model Probing

Open paper AskPDF arXiv

Accurate evaluation of user satisfaction is critical for iterative development of conversational AI. However, for open-ended assistants, traditional A/B testing lacks reliable metrics: explicit feedback is sparse, while implicit metrics are ambiguous. To bridge this gap, we introduce BoRP (Bootstrapped Regression Probing), a scalable framework for high-fidelity satisfaction evaluation. Unlike generative approaches, BoRP leverages the geometric properties of LLM latent space. It employs a polarization-index-based bootstrapping mechanism to automate rubric generation and utilizes Partial Least Squares (PLS) to map hidden states to continuous scores. Experiments on industrial datasets show that BoRP (Qwen3-8B/14B) significantly outperforms generative baselines (even Qwen3-Max) in alignment with human judgments. Furthermore, BoRP reduces inference costs by orders of magnitude, enabling full-scale monitoring and highly sensitive A/B testing via CUPED.