Large language model choices shift when extra context is added
Reading Too Much into Context: Passive Exposure Can Steer LLM Decisions
Computation and LanguageMachine Learning
Summary
Large language models (LLMs) can look up information from outside sources while answering questions. The authors found that simply adding extra content to the model’s context can change its decisions, even if that content shouldn’t affect the answer. This change in behavior happens across different models and can cause the model to ignore user instructions or believe false information. The study shows that what the model sees matters a lot, sometimes too much, when making decisions.
What this means in practice
- •For llm application developers: Improve reliability of LLM assistants by accounting for unintended context influences when integrating external sources.
- •For content moderation teams: Enhance detection of when LLMs accept false claims due to passive exposure in context, reducing misinformation risks.
Authors
Yuxiang Zheng, Lin Tian, Marian-Andrei Rizoiu
Abstract
Large language model (LLM) assistants can now search the web and consult external sources while completing user requests. These sources can provide useful evidence, but they can also introduce additional content into the model's context. Can such passive exposure steer a decision even when the added content provides no reason to change it? We examine the stability of model decisions on the same tasks with and without such external content. Across all open-weight and closed-weight models we test, exposure systematically shifts decisions, with effects reaching nearly 50 percentage points in closed-weight models. The same pattern appears with real-world online opinions. The influence also extends beyond subjective preferences. Such exposure can steer models toward choices that violate explicit user requirements and increase their acceptance of false claims. In short, what enters an LLM's context can influence its decision even when it should not determine it.