Anchoring Bias in Language Models

Follow this topic Ask about this topic

Latest papers

8 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved Analysis
Nov 3, 2026Yanru Xiao, Yingwei YuAnchoring Bias in Language Models Cognitive Bias in Language Models
Amazon Web Services
Multi-Estimate Elicitation Does Not Uniformly Debias Language Model Judgments
Oct 31, 2026An-Sheng JhangAnchoring Bias in Language Models Cognitive Bias in Language Models
Dongguan University of Technology
LLMs Anchor on Chief Complaint and Fail to Integrate Evidence in Sequential Clinical Triage
Sep 19, 2026Dipankar Srirag, Haokai Zhao, Ashutosh Kumar +6Clinical Triage Clinical Reasoning
University of New South Wales, Sydney · Independent Researcher · St Vincent’s Hospital, Sydney +2
Localizing Anchoring Pathways in Language Models
Jun 11, 2026Hillary N. Owusu, Sarah Wiegreffe, Naomi H. FeldmanNumerical Reasoning in Language Models LLM Interpretability
University of Maryland, College Park
Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation
May 9, 2026Jikun Wu, Dongxin Guo, Siu-Ming YiuComputational Cognitive Modeling Autoregressive Language Modeling
1Stellaris AI Limited, Hong Kong, China · 3The University of Hong Kong, Hong Kong, China
12 Angry AI Agents: Evaluating Multi-Agent LLM Decision-Making Through Cinematic Jury Deliberation
May 3, 2026Ahmet Bahaddin ErsozLLM Alignment LLM Agent Evaluation
∗ORCID: 0000-0001-6297-7501
Prompt Framing Distorts Count-Based Evaluation of LLM Error Detection: Evidence from Numeric Anchoring
May 3, 2026Dekun YangPrompt Sensitivity LLM Evaluation
Zhejiang University
Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference
Feb 23, 2026Arindam KhaledAnchoring Bias in Language Models LLM Routing
Independent Researcher

Nov 3, 2026J/K move · Enter open · S save

Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved Analysis

Yanru Xiao, Yingwei Yu

Amazon Web Services

Anchoring Bias in Language Models Cognitive Bias in Language Models LLM Agent Reliability Agentic Retrieval

Open paper AskPDF arXiv

Search can help LLM agents correct mistakes, but their starting conditions may shape which evidence they find and use. Drawing on cognitive-bias paradigms, we develop a controlled search harness to examine result order, records of prior work, and initial hypotheses while holding each question and document collection fixed. Matched controls distinguish order effects from differences in document composition and the effects of failed work from context length. Across 10 models and 1,000 synthetic search worlds, we track queries, retrieved documents, document openings, and final answers. Our comparisons suggest that final answers are more sensitive to initial evidence order during active search than when all evidence is supplied in full. Dead-end histories can reduce strategy switching relative to matched neutral histories, indicating an effect beyond context length. Under wrong hypotheses, stage measurements distinguish reduced retrieval or opening from errors that persist after counter-evidence is opened. Exploratory interventions show that opening counter-evidence more often can coincide with lower accuracy, while accuracy can improve with little change in opening.