Paper

"Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms

Unreadunread

AI summary

arXiv:2606. 12618v1 Announce Type: new Abstract: Robust lie detectors for language models could enable powerful techniques for auditing, monitoring, and post-hoc investigation of model behaviour, but evaluating them requires testbeds where models verifiably believe the opposite of what they say.

Reading status

Priority

About this paper

Authors: Alan Cooney, David Africa, Geoffrey Irving
Released: 2026-06-12 (27d ago)
Topic: Related to current project
Relation to my work: Read next because "Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: strong, class, rect, eval, follow-up, chain, trained, capability. Source: arxiv cs.AI (Artificial Intelligence).
arXiv: 2606.12618

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to "Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.