Year: 2026
Type: conference-paper
Abstract: Anchoring bias causes large language models (LLMs) to shift quantitative judgments in response to irrelevant numerical primes.We analyze this bias as a function of model confidence and accuracy in base, instruction-tuned, and distilled variants of Llama and Qwen models.We find that anchoring susceptibility is negatively correlated with model confidence without regard to accuracy: confidently incorrect models resist anchoring as effectively as accurate ones, provided their internal priors are sufficiently strong.We further show that post-training impacts the strength of this relationship, and that models are more susceptible to high anchors than to low anchors.Our findings suggest anchoring resistance is a structural property of distributional concentration (certainty) rather than knowledge correctness (factual accuracy), with implications for deploying LLMs in numerical reasoning tasks.
Authors: Hillary N. Owusu, Naomi H. Feldman
Institution: University of Maryland, College Park
Language: English
Subfield: General Decision Sciences
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W7166835177