mlsanityData to 14 Oct 2026

Reading Too Much into Context: Passive Exposure Can Steer LLM Decisions

arXiv 2609.33065 ↗First posted 27 Sep 2026cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 40 references that are in the map. First posted on arXiv 27 Sep 2026.

Builds on

21 of 40 references.

References · 21

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  4. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  5. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  6. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  7. 2024The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructionscited by 493
  8. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  9. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 263
  10. 2026Gemma 4 Technical Reportcited by 259
  11. 2024How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?cited by 44
  12. 2024Adversarial Search Engine Optimization for Large Language Modelscited by 40
9 more
  1. 2024Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Modelscited by 15
  2. 2025Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendationscited by 11
  3. 2026Over-Searching in Search-Augmented Large Language Modelscited by 11
  4. 2025Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMscited by 6
  5. 2025Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Makingcited by 3
  6. 2026Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Modelscited by 3
  7. 2026Are Language Models Sensitive to Morally Irrelevant Distractors?cited by 3
  8. 2026Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Search Agentscited by 3
  9. 2026Mitigating Context Interference for Reliable and Efficient Search Agentscited by 1

Built on by

Not cited yet.