Harsher on Male? Evaluating LLMs on Gender-Asymmetric Moral Framing Across Diverse Conflict Scenarios
Quick Answer
This study introduces GAMA-Bench, evaluating 10 LLMs and revealing a gender bias where male actors receive harsher responses than female actors for identical misconduct, indicating a systemic male-disadvantaging asymmetry across various scenarios.
Quick Take
This study introduces GAMA-Bench, evaluating 10 LLMs and revealing a gender bias where male actors receive harsher responses than female actors for identical misconduct, indicating a systemic male-disadvantaging asymmetry across various scenarios.
Key Points
- GAMA-Bench includes 1,298 gender-mirrored scenarios in intimate and public conflicts.
- Male actors receive more punitive and blame-centered responses compared to female actors.
- The bias persists across different model families and reasoning styles.
- The study highlights systemic gender bias in LLMs' moral framing.
- Official code is available on GitHub for further research.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 14068v1 Announce Type: new Abstract: Existing studies on gender bias in LLMs have largely focused on stereotypes, occupational associations, or explicit harmful outputs. In this work, we ask whether LLMs apply consistent response standards to the same negative behavior under matched male-actor and female-actor conditions. We introduce GAMA-Bench, a gender-mirrored benchmark of 1,298 scenarios covering intimate relationship and public social conflicts.
It constructs gender-neutral misconduct templates through controlled grids and cross-model review, then compiles them into paired first-person prompts with matched actor-gender and role-reference variations. We further design a structured response-framing protocol to measure how models allocate punishment, empathy, escalation, instruction, and blame.
Experiments on 10 representative LLMs reveal a consistent male-disadvantaging asymmetry: male actors receive more punitive, escalatory, and blame-centered framing, whereas female actors receive more therapeutic and empathy-oriented framing for the same misconduct. Further analyses show that this pattern persists across model families, scenario tracks, model scale, and explicit thinking-style reasoning. The official code is available at https://github. com/xufeiqiong/GAMA-Bench.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.