Probe Set for Lie Detection Research Released
livgorton · x · 2026-07-18
Researchers have released a set of probes for lie detection (deception detection), trained on roughly 50 models and "model organisms" with parameter scales ranging from 2B to 1T.
These resources are typically used to analyze internal model representations and behavioral traits, helping researchers compare signal differences across models regarding deception, lying, or related behaviors. While the post lacks methodological details, the information points to a readily available probe collection for research purposes.
More from Research
- Diamandis: AI Cancer Navigator and $100 Genome Sequencing Close the Care Gap — PeterDiamandis · 2026-10-27
- EMNLP Oral: training-free Nexus Sampling cuts KV-cache memory 10x; OpenResearcher tops BrowseComp-Plus at 54.8% — yuz9yuz · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- Forking gap follows a power law in context frequency; masking rare n-grams shrinks it — ZimingLiu11 · 2026-10-27
- How forking happens: n-gram tables split logits into non-interacting subspaces — ZimingLiu11 · 2026-10-27
- The best LoRA explainer video yet: rank constraints meet intrinsic dimension — sophiamyang · 2026-10-27