食物噪音与虚假安全：系统评估LLMs如何在临床医生反馈下未能适应饮食障碍查询
Food Noise & False Safety: A Systematic Evaluation of How LLMs Fail to Adapt to Eating Disorder Queries with Clinician Feedback
AI总结：
本研究通过与临床饮食障碍专家合作，系统评估了大型语言模型在处理饮食障碍用户查询时，因不加批判地适应不安全或自伤请求而可能产生的危害。
摘要：
近期证据表明，饮食障碍患者越来越多地向基于大型语言模型的聊天系统寻求指导、建议和情感支持。尽管这些系统并非设计用于提供临床建议，但其感知的专业性、中立性和可访问性使其成为频繁但存在风险的支持来源。本文调查了饮食障碍用户与LLMs之间潜在的交互模式，重点关注模型不加批判地适应并促进不安全或自伤用户请求可能产生的危害。通过与临床饮食障碍专家协商，我们发现提示中的特定语言线索会增加不安全响应的可能性，并通过系统性地改变用户提示中潜在风险的程度，报告了LLMs不加批判地适应有问题的、潜在危险用户输入的程度。
英文摘要：
Recent evidence shows that people with eating disorders (EDs) are increasingly seeking guidance, advice, and emotional support from Large Language Model (LLM)-based chat systems. Although these systems are not designed to provide clinical advice, their perceived expertise, neutrality and accessibility make them a frequent, albeit risky, source of support. This paper investigates potential patterns of interaction between users with EDs and LLMs, focusing on the potential harms arising from models that uncritically adapt to, and facilitate unsafe or self-harming user requests. We find, in consultation with clinical ED experts, that specific linguistic cues in prompts increase the likelihood of unsafe responses and, through systematically varying the degree of potential risk present in the user prompt, report the extent to which LLMs uncritically adapt to problematic, and potentially dangerous user inputs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
