cs.AI updates on arXiv.org 12小时前
Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出PERSIST框架,对25+大型语言模型进行行为稳定性评估,发现模型存在大量响应变异,挑战了当前部署假设,对安全关键应用提出警示。

arXiv:2508.04826v1 Announce Type: cross Abstract: Large language models require consistent behavioral patterns for safe deployment, yet their personality-like traits remain poorly understood. We present PERSIST (PERsonality Stability in Synthetic Text), a comprehensive evaluation framework testing 25+ open-source models (1B-671B parameters) across 500,000+ responses. Using traditional (BFI-44, SD3) and novel LLM-adapted personality instruments, we systematically vary question order, paraphrasing, personas, and reasoning modes. Our findings challenge fundamental deployment assumptions: (1) Even 400B+ models exhibit substantial response variability (SD > 0.4); (2) Minor prompt reordering alone shifts personality measurements by up to 20%; (3) Interventions expected to stabilize behavior, such as chain-of-thought reasoning, detailed personas instruction, inclusion of conversation history, can paradoxically increase variability; (4) LLM-adapted instruments show equal instability to human-centric versions, confirming architectural rather than translational limitations. This persistent instability across scales and mitigation strategies suggests current LLMs lack the foundations for genuine behavioral consistency. For safety-critical applications requiring predictable behavior, these findings indicate that personality-based alignment strategies may be fundamentally inadequate.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

大型语言模型 行为稳定性 PERSIST框架 模型评估 安全应用
相关文章