method · first seen 6 Oct 2026
representation probing
Also: probing, probing classifiers, concept-based model monitoring, probing of internal representations, linear probing of vision-language model layers, linear probing of self-supervised speech models
Training simple classifiers on frozen model activations to test what information a network encodes internally.
Mentions per week
PapersCodeDiscussion
Rank 88 on 16 Nov 2026 · 7 mentions in 28 days · 7 independent groups · papers · first seen 6 weeks ago · acceleration +1.90
Earliest sources
- Feature Encoding in VAE-based Audio Decoders: Effects of Input, Depth and DistributionPapers · 6 Oct 2026 · Louis McCallum, Mick Grierson
- Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing MethodologyPapers · 8 Oct 2026 · Zhaoxin Yu, Qingchao Kong, Dajun Zeng, Wenji Mao
- When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical PriorsPapers · 9 Oct 2026 · Shubh Garg, Chen Shani
- Do LLMs differentiate linguistic traits internally?: A layer-wise analysisPapers · 10 Oct 2026 · Samhita Bollepally, Takashi Yamauchi, Manju Muralee, Motunrayo Adebimpe
- The belief-action gap in language model agentsPapers · 12 Oct 2026 · Ayse Sila Okcu, Weisheng Wang, Tongmeng Xie, Niall Dalton, Angelos Nalmpantis, R…
- Probing the Geometry of Color Representations in Multilingual Language ModelsPapers · 13 Oct 2026 · Pablo Loyola, Edison Marrese-Taylor, Andrés Hoyos-Idrobo
Latest sources
- Geometrically Disentangling Concept Learning from the Language Modeling LossPapers · 13 Nov 2026 · Yupei Wang, Neil Mallinar, Mikhail Belkin, Alex Warstadt
- How Post-Training Influences Verbalized Algorithmic Computation in Language ModelsPapers · 10 Nov 2026 · Niall Dalton
- Understanding When and Where Self-Supervised Speech Models Learn Phonemes and Prosodic Cues through Layer-Wise and Time-Resolved ProbingPapers · 8 Nov 2026 · Masaru Tanibata, Shun Takahashi, Hiroki Ouchi, Sakriani Sakti
- Tracing Psychometric Inference in Large Language ModelsPapers · 6 Nov 2026 · Chih-Hao Hsu, Feng-Chun B. Chou, Pin-Hao A. Chen
- Shaping & Monitoring Models through their Internal RepresentationsPapers · 4 Nov 2026 · Thomas Fel, Matthew Kowal, Matt Feiszli, Satchel Grant, Andrew Lee, Chris Earls,…
- Encoded but Unused: Bounding the Sources of VLM ErrorsPapers · 21 Oct 2026 · Anat Veikherman, Mor Ventura, Nitay Calderon, Lihi Zelnik-Manor, Roi Reichart
- Copied, Mixed or Computed? Testing Latent Intermediate Values with Minimal PairsPapers · 20 Oct 2026 · Aur Shalev Merin
- Do LMs Know What Variables Do? Interpreting Code Representations via Variable RolesPapers · 16 Oct 2026 · Célian Vasson, Daniil Ognev, Kentaro Inui, Benjamin Heinzerling
- Does Latent Chain-of-Thought Actually Reason? A Single, Unifying Taxonomy for Latent ReasoningPapers · 15 Oct 2026 · Jingjie Qiu, Sheldon Yu, Xunyi Jiang, Jiajin Liu, Zihan Huang, Zhendong Chu, Ton…
- Taking the PULSE of Medical Reasoning: Step-Level Retrieval Timing for Knowledge-Grounded InferencePapers · 14 Oct 2026 · Danyang Zhao, Sendong Zhao, Yanrui Du, Haochun Wang, Ming Ma, Wenhao Li, Jingbo…
- Probing the Geometry of Color Representations in Multilingual Language ModelsPapers · 13 Oct 2026 · Pablo Loyola, Edison Marrese-Taylor, Andrés Hoyos-Idrobo
- The belief-action gap in language model agentsPapers · 12 Oct 2026 · Ayse Sila Okcu, Weisheng Wang, Tongmeng Xie, Niall Dalton, Angelos Nalmpantis, R…