Conditional Cognitive Biases in LLMs: How Biased User Turns Modulate In-Context Reasoning
arXiv:2608.05166v1 Announce Type: cross Abstract: We present an evaluation of cognitive bias expression in state-of-the-art instruction-tuned LLMs under realistic multi-turn interaction settings. Our work introduces a novel three-condition experimental framework that disentangles the effect of exposure to a biased user turn from the effect of the turn's semantic content, alongside a benchmark of 24,300 jury-validated user prompts spanning all 81 cells of a 9x9 target-human bias interaction matri
Record details
Published: 7 August 2026
Source: arXiv cs.CY
Category: Research
Topics: Bias & fairness
Retrieved: 7 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Who Gets Access? Global Region and Academic Status Bias in AI-Generated Academic Gatekeeping Scenarios
arXiv cs.CY · 7 August 2026
Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests
arXiv · 7 August 2026
Stream Learning: Partition-Fair Gossip Learning Without Tokens
arXiv fairness query · 7 August 2026
Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning
arXiv cs.CR (AI security) · 6 August 2026
Challenges in Evaluating Explanation Methods for Static and Evolving Data
arXiv cs.AI · 6 August 2026
Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors
arXiv · 6 August 2026
How to cite this record
ethics.ai (7 August 2026), “Conditional Cognitive Biases in LLMs: How Biased User Turns Modulate In-Context Reasoning,” evidence record 17018, https://ethics.ai/record/17018 (originally published by arXiv cs.CY).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.