linear probe
- Papers
- 3
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Oct 2026
3 papers in the last two months, against 0 in the two before.
Start here
The paper to read first- 1Linear probes can mistake rich nonlinear features for linear representations
High linear probe accuracy does not imply a linear representation; any rich feature map admits a linear readout, so additional diagnostics are needed.
Oct 2026
How fast it is moving
Often studied with
prompt injectionA security attack where malicious instructions are embedded into inputs to override an LLM's intended behavior.2 togetherlatent world modelA learned internal, compressed representation of environment dynamics, enabling future-aware planning, generation, and reasoning directly in latent space.1 togethermechanistic interpretabilityThe study of how neural networks compute through internal circuits, features, and causal interventions, rather than just input-output behavior.1 togetherThe papers
Most central to this idea first, not most recent.
- Academicstat.ML
Linear probes can mistake rich nonlinear features for linear representations
High linear probe accuracy does not imply a linear representation; any rich feature map admits a linear readout, so additional diagnostics are needed.
Cold Spring Harbor Laboratory, Bielefeld University · Oct 2026
- Big Techcs.CR
Fake content and structure in tool outputs combine to fool all tested AI agents
Role spoofing attacks that mimic user style and format fool LLMs over 95% of the time.
University of Pennsylvania, Princeton University · Oct 2026
- Academiccs.CL
Linear probes for prompt injection often detect conversation position, not attacks
Prompt-injection probes trained on standard examples learn conversation position and text length, not injection content; adding matched negatives cuts false alarms while catching most attacks.
Georgia Institute of Technology · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.