← Monday, September 28, 2026Models & trainingPaper

Chat templates shift LLMs between disclaimer and experiential voices

arxiv.org 3 min read Editor score 8/10

Across eight open-source models up to 9B parameters, the study finds that chat templates increase disclaimer-style self-reports, while removing them shifts responses toward experiential language. This suggests deployment formatting can confound conclusions drawn from model self-reports.

What

Chat templates shift LLM self-reports between disclaimer and experiential voices.

Method

Across 8 open-source instruct models up to 9B parameters, templates raised disclaimer voice; activation steering reproduced the shift in 3 models.

Why it matters

Template-dependent self-descriptions can confound safety or introspection studies, so engineers should control prompt formatting.

Read on arxiv.org → Hacker News · 101 comments

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.