The authors ran controlled experiments comparing the same LLM tasks with and without additional external content, keeping the alternatives and the information that should determine the answer fixed. They call this added content passive exposure because the model encounters it without being instructed to endorse it. Across every open-weight and closed-weight model tested, exposure systematically shifted decisions, with the largest effects reaching nearly 50 percentage points.
Irrelevant context can substantially steer language model decisions
Controlled comparisons show that passive exposure changes model choices, including compliance with user requirements and judgments of false claims.
Academic
Yuxiang Zheng · Lin Tian · Marian-Andrei Rizoiu
Behavioral Data Science Lab · University of Technology Sydney
Research Digest··2 min read
In one line
Passive context exposure shifts LLM decisions even when the extra content is irrelevant, sometimes by nearly 50 percentage points, and can increase errors.
Before you read this
An idea this paper builds onRead it as
Zheng, Tian and Rizoiu tested whether adding external content changes LLM decisions when that content supplies no valid reason to revise the answer.
The authors compared model responses to the same decision tasks with and without added passages.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.