Paper

Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs

Unreadunread

AI summary

arXiv:2605. 23039v1 Announce Type: new Abstract: How do learners acquire knowledge of what is unacceptable without negative evidence?

Reading status

Priority

About this paper

Authors: Dongxin Guo, Jikun Wu, Siu Ming Yiu
Released: 2026-05-25 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs 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, latin, rect, distributional, rate, control, without, test. Source: arxiv cs.CL (NLP).
arXiv: 2605.23039

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.