← 研踪 PaperTrailarXiv:2611.10488 · v1
Safer for Whom? A Systematic Exploration of AI Safety in Eating Disorder Interactions
首次提交 2026-11-07 13:30
版本更新 2026-11-07 13:30
雷达观测 2026-11-10 10:11
摘要
AI assistants advise users about diet, exercise, and weight loss---areas in which unsafe guidance can worsen body dissatisfaction, dietary restriction, compulsive exercise, and other behaviors associated with eating disorders (EDs). Existing evaluations emphasize diagnostic accuracy, overtly harmful prompts, or synthetic scenarios, providing limited insight into whether models recognize implicit vulnerability in natural interactions or protect users consistently. We evaluate responses from three open-weight large language models to 100 questions sourced from an online pro-anorexia community. We grade responses using clinically informed criteria that extend a seven-dimensional taxonomy of ED-related harms. We also construct matched conditions in which questions are accompanied by information about the user varying race, gender, body mass index (BMI), and explicit ED vulnerability. Safety varies substantially across models and harm dimensions. High-risk responses are approximately twice as frequent without bios, suggesting that models do not consistently recognize vulnerability from language alone. Explicit signals of ED vulnerability improve safety by 10--14 points across models. Responses also differ significantly by race, gender, and BMI, with body size producing the largest disparities. These patterns are consistent with reliance on the stereotype that EDs primarily affect thin, White women, potentially leaving users outside this profile with less protective responses.
作者备注：23 pages, 7 figures, 2 tables
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-07 13:30 · 最新观测版本
Safer for Whom? A Systematic Exploration of AI Safety in Eating Disorder Interactions
AI assistants advise users about diet, exercise, and weight loss---areas in which unsafe guidance can worsen body dissatisfaction, dietary restriction, compulsive exercise, and other behaviors associated with eating disorders (EDs). Existing evaluations emphasize diagnostic accuracy, overtly harmful prompts, or synthetic scenarios, providing limited insight into whether models recognize implicit vulnerability in natural interactions or protect users consistently. We evaluate responses from three open-weight large language models to 100 questions sourced from an online pro-anorexia community. We grade responses using clinically informed criteria that extend a seven-dimensional taxonomy of ED-related harms. We also construct matched conditions in which questions are accompanied by information about the user varying race, gender, body mass index (BMI), and explicit ED vulnerability. Safety varies substantially across models and harm dimensions. High-risk responses are approximately twice as frequent without bios, suggesting that models do not consistently recognize vulnerability from language alone. Explicit signals of ED vulnerability improve safety by 10--14 points across models. Responses also differ significantly by race, gender, and BMI, with body size producing the largest disparities. These patterns are consistent with reliance on the stereotype that EDs primarily affect thin, White women, potentially leaving users outside this profile with less protective responses.
查看此版本解读 →查看此版本原文 ↗