研究：LLM 对进食障碍用户的保护因种族、性别、BMI 而异
Safer for Whom? A Systematic Exploration of AI Safety in Eating Disorder Interactions
拿100个真实厌食症社区的问题去测三个开源模型，还改用户背景做对照。结果挺扎眼：不告诉模型用户情况时，危险回答翻倍；体型不同得到的保护也不一样。做 AI 安全或医疗方向的人应该看看这套评估方法。
arXiv 论文《Safer for Whom?》评估了三个开源权重 LLM 对 100 个来自厌食症网络社区的问题的回答，并采用扩展自七维进食障碍伤害分类的临床标准进行打分。
研究还设置了对照组，在问题旁附上包含用户种族、性别、BMI 和明确进食障碍易感性的个人信息。结果显示：无个人信息时高风险回答频率约为有信息时的两倍；明确标注易感性后各模型安全性提升 10–14 个百分点。
回答质量随种族、性别和 BMI 显著变化，其中体型造成的差异最大，作者认为这与“进食障碍主要影响瘦的白人女性”的刻板印象一致，意味着不符合该形象的用户得到的保护更少。
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.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI regulation, compliance frameworks, and sovereign compute policy. Key entities and technical topics under continuous tracking include LLM安全, 进食障碍, AI公平性, 开源模型.
Source attribution: curated from arXiv cs.AI (@Jinyuan Wang, Minh Duc Chu, Frances Ross, Ellen Fitzsimmons-Craft, Kristina Lerman).