Paper

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs

Unreadunread

AI summary

arXiv:2605. 20382v1 Announce Type: new Abstract: Language models are trained to follow instructions, but they are also powerful pattern completers.

Reading status

Priority

About this paper

Authors: Carolina Camassa, Derek Shiller
Released: 2026-05-21 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because Do as I Say, Not as I Do: Instruction-Induction Conflict 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: code, persona, rect, under, correct, assistant, token, rate. Source: arxiv cs.CL (NLP).
arXiv: 2605.20382

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.