method · first seen 4 Oct 2026
linear probing
Also: probes, linear probe, linear readout, diagnostic probes, frozen feature probing, residual-stream probes, layerwise linear probes
Evaluating representations by training a linear classifier on frozen hidden states to test whether information is recoverable.
Mentions per week
PapersCodeDiscussion
Rank 143 on 16 Nov 2026 · 56 mentions in 28 days · 55 independent groups · papers · first seen 6 weeks ago · acceleration -0.24
Earliest sources
- ContractLens: Latent Security Knowledge for Malicious Smart Contract DetectionPapers · 4 Oct 2026 · Shuyi Miao, Xinyi Huang, Wangjie Qiu, Fei Shen, Jinchun He, Zhiming Zheng, Tat-S…
- What Does an Observability Foundation Model Know?Papers · 4 Oct 2026 · Dhyey Dharmendrakumar Mavani, Rian Atri, Tairan Ji
- What the Guard Misses, the Robot Executes: Implied Harm in VLA InstructionsPapers · 5 Oct 2026 · Sripad Karne, Arjun Balaji
- Do VLAs Understand and Adapt to the Objects They Handle, or Simply Replay Learned Behaviors?Papers · 5 Oct 2026 · Xinnuo Xu
- Anosognosia in LLMs: Probing Self-Awareness of Quantized Computational SubstratePapers · 5 Oct 2026 · Yoshihiro Izawa, Gouki Minegishi, Yoko Yamakata
- Loss-Invariant Projections as Passive Probes of Learned RepresentationsPapers · 5 Oct 2026 · Akshay Chandrasekhar, Pavlo Melnyk
Latest sources
- Out-of-training properties in frozen interatomic potential embeddings are decodable and ordered by physical scalePapers · 16 Nov 2026 · Natalija Stepurko, Joonatan E. M. Laulainen
- Pretty Linear Liars: Unregularized Probes Favor Intervention-Unfaithful FeaturesPapers · 16 Nov 2026 · Karl Vilhelmsson Emneby, Julian Yocum, Cameron Allen
- Early Readability of Trajectory Quality in Diffusion Driving PlannersPapers · 15 Nov 2026 · Xiang Zhang, Ziyang Leng, Yuxin Bao, Zhihao Zhao, Bolei Zhou, Xugui Zhou
- Beyond the Training Cameras: Coverage-Controlled Probes of Viewing Direction in Frozen Vision ModelsPapers · 14 Nov 2026 · Peize Ding
- Do Probing and Steering Favor the Same Directions Within and Across Language Models?Papers · 14 Nov 2026 · Afshin Sadeghi, Daniel Becker
- A Bag of Concepts? Testing Role-Filler Binding in the Verbalizable WorkspacePapers · 14 Nov 2026 · Reya Dawlah, Elizabeth McMillin, Michael Shihong Zhang, Badrish Ananth, Rishi Ad…
- Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element HallucinationPapers · 13 Nov 2026 · Mohamed Aghzal, Mor Geva, Gregory J. Stein, Ziyu Yao
- V-JEPA-LM: Video-Language Models That Read Dynamics Beyond Static, Text-Aligned RepresentationsPapers · 13 Nov 2026 · Keuntae Kim, Dongjun Kim, Yong Suk Choi
- Where to Predict in Retinal OCT? Anatomy-Guided Target Selection for I-JEPAPapers · 12 Nov 2026 · Yunchu Feng, Wai Tak Lau, Kaveri A. Thakoor
- Detection Is Not Early Warning: Evaluating Token-Level Alarms on Language Model FailuresPapers · 12 Nov 2026 · Marco De Negri, Luca Sartori, Lorenzo Baggi, Moritz Reihs, Eduard Frank Ďurech,…
- Sophon: A Procedural Diagnostic for Spatial Reasoning in Vision-Language ModelsPapers · 10 Nov 2026 · J. Zach Gazak, Ryan Swindle, Justin Fletcher
- Auditing the Judge: Internal Signals for LLM Reasoning AssurancePapers · 10 Nov 2026 · Mayank Gulati, Gerhard Wunder
Mentioned together with
In the ledger
- 2026-W47 · baseline #4 · already mainstream · 360 news articles in 30 days mention "probes" (GDELT)