Paper

As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs

Unreadunread

AI summary

arXiv:2605. 23147v1 Announce Type: new Abstract: Role prompts of the form As X, do Y admit a clean linear decomposition at one specific site in the residual stream: the prompt-to-answer transition -- the last prompt token together with the first two generated tokens -- in an early/mid layer band.

Reading status

Priority

About this paper

Authors: Eric Xu
Released: 2026-05-25 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because As X, Do Y: How Persona and Task Combine in Instruction-Tuned 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: marker, text, persona, rect, token, line, rate, does. Source: arxiv cs.CL (NLP).
arXiv: 2605.23147

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.