Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Yangyang, Yu, Dong, Liu, Pengyuan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2606.02214
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917555361284096
author Liu, Yangyang
Yu, Dong
Liu, Pengyuan
author_facet Liu, Yangyang
Yu, Dong
Liu, Pengyuan
contents Large language models are increasingly used in value-sensitive decision settings, where irrelevant demographic cues should not alter judgments. We construct the Realistic Value Decision Benchmark (RVDB), a controlled benchmark that varies only the role-gender configuration while holding the scenario, ordered value pair, roles, candidate decisions, Value Distance, and Decision Severity fixed. Using a position-balanced evaluation across seven models, we test whether models preserve decision invariance under gender perturbations and whether their self-attributions reflect observed behavioral changes. We find that explicit gender cues induce bounded but systematic decision flips, including under an explicit gender-attribution prompt that asks models to report whether gender influenced their choice. Cross-gender role swaps reveal a consistent female-proposed-decision asymmetry, while models often attribute flipped decisions to No Influence or other non-gender factors. Further analysis shows that gender effects concentrate near less determinate value boundaries and under more severe decision contexts, suggesting that gender cues act as local boundary-shifting factors rather than global overrides of value reasoning. Value rankings remain largely stable, but ordered value-pair trade-offs shift unevenly across role-gender configurations. These results show that gender can enter LLM value trade-offs behaviorally while remaining obscured in self-attribution, motivating controlled behavioral audits beyond explanation-based evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2606_02214
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Do Gender Cues Affect LLM Value Trade-offs? Evidence from a Controlled Decision Benchmark
Liu, Yangyang
Yu, Dong
Liu, Pengyuan
Computation and Language
Large language models are increasingly used in value-sensitive decision settings, where irrelevant demographic cues should not alter judgments. We construct the Realistic Value Decision Benchmark (RVDB), a controlled benchmark that varies only the role-gender configuration while holding the scenario, ordered value pair, roles, candidate decisions, Value Distance, and Decision Severity fixed. Using a position-balanced evaluation across seven models, we test whether models preserve decision invariance under gender perturbations and whether their self-attributions reflect observed behavioral changes. We find that explicit gender cues induce bounded but systematic decision flips, including under an explicit gender-attribution prompt that asks models to report whether gender influenced their choice. Cross-gender role swaps reveal a consistent female-proposed-decision asymmetry, while models often attribute flipped decisions to No Influence or other non-gender factors. Further analysis shows that gender effects concentrate near less determinate value boundaries and under more severe decision contexts, suggesting that gender cues act as local boundary-shifting factors rather than global overrides of value reasoning. Value rankings remain largely stable, but ordered value-pair trade-offs shift unevenly across role-gender configurations. These results show that gender can enter LLM value trade-offs behaviorally while remaining obscured in self-attribution, motivating controlled behavioral audits beyond explanation-based evaluation.
title Do Gender Cues Affect LLM Value Trade-offs? Evidence from a Controlled Decision Benchmark
topic Computation and Language
url https://arxiv.org/abs/2606.02214