Metraipolis › archive › dc_d002a5ce9339
Measuring Human-Like Bias in LLMs? A Critique of Human-Derived Bias Constructs in LLM Evaluation — arXiv:2610.00070
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00070
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T13:53:34.244Z
- SHA-256 of the archived text
1312016b451e00835b4e8434b92bf669d7c6d662ada6df99bc6610b9205baad0- Stable URL of this page
https://metraipolis.com/documento/dc_d002a5ce9339
How to cite
Measuring Human-Like Bias in LLMs? A Critique of Human-Derived Bias Constructs in LLM Evaluation — arXiv:2610.00070 — arXiv (en), https://arxiv.org/abs/2610.00070 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d002a5ce9339 (Metraipolis archive dc_d002a5ce9339, sha256 1312016b451e00835b4e8434b92bf669d7c6d662ada6df99bc6610b9205baad0)
BibTeX
@misc{dcd002a5ce9339,
title = {Measuring Human-Like Bias in LLMs? A Critique of Human-Derived Bias Constructs in LLM Evaluation — arXiv:2610.00070},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00070},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d002a5ce9339; sha256 1312016b451e00835b4e8434b92bf669d7c6d662ada6df99bc6610b9205baad0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00070. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Researchers increasingly use human-derived bias constructs to study Large Language Models (LLMs), including social-cognitive constructs such as implicit bias and stereotype activation, and cognitive biases such as anchoring, framing effects, and confirmation bias. Such approaches offer alternatives to overt bias probes, particularly when direct questioning may obscure bias or when model behaviour appears normatively acceptable. However, adapting human bias constructs to LLMs introduces an inferential gap. Psychological instruments were developed to study human cognition and social behaviour, whereas LLM evaluations rely on probabilities, text completions, rankings, or simulated decisions. This paper critiques human-centered bias evaluation in LLMs. We show how this gap arises from mismatches pertaining to human-derived constructs, human-model differences, and evaluation contexts, which can blur distinct interpretations of model bias. We then introduce a framework providing an analytical lens for relating these elements to warranted interpretations, with attention to target constructs, operationalizations, scope of inference, and limits of human analogy. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.00070 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T12:15:34.597Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).