EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Anchoring bias in large language models: an experimental study

Jiaxu Lou, Yifan Sun

Journal of Computational Social Science · 2026-02 · 9 (1)

DOI: 10.1007/s42001-025-00435-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computational Social Science, online erschienen am 05.12.2025. Verfasst von Jiaxu Lou und 1 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Language Models (LLMs) like GPT-4 and Gemini have significantly advanced artificial intelligence by enabling machines to generate and comprehend human-like text. Despite their impressive capabilities, LLMs are not without limitations. They exhibit various biases. Although much research has explored demographic biases, cognitive biases in LLM have not been equally studied. This study delves into anchoring bias, a cognitive bias in which initial information disproportionately influences judgment. Using an experimental data set, we examine how anchoring bias manifests in LLM and verify the effectiveness of various mitigation strategies. Our findings highlight the sensitivity of LLM responses to biased prompts. At the same time, our experiments show that to mitigate anchoring bias, one needs to collect information from comprehensive angles to prevent the LLMs from being anchored to individual pieces of information, as simple algorithms such as Chain-of-Thought, Thoughts of Principles, Ignoring Anchor Hints, and Reflection are insufficient.

Zitieren

APA

Lou, J., & Sun, Y. (2026). Anchoring bias in large language models: an experimental study. Journal of Computational Social Science, 9(1). https://doi.org/10.1007/s42001-025-00435-2

Vancouver

Lou J, Sun Y. Anchoring bias in large language models: an experimental study. Journal of Computational Social Science. 2026;9(1). doi:10.1007/s42001-025-00435-2

BibTeX
@article{Lou2026,
  author = {Lou, Jiaxu and Sun, Yifan},
  title = {Anchoring bias in large language models: an experimental study},
  journal = {Journal of Computational Social Science},
  year = {2026},
  volume = {9},
  number = {1},
  doi = {10.1007/s42001-025-00435-2}
}
Kostenlos starten →