cs.AI updates on arXiv.org 23小时前
On the Fundamental Impossibility of Hallucination Control in Large Language Models
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

arXiv:2506.06382v1 Announce Type: cross Abstract: This paper explains \textbf{why it is impossible to create large language models that do not hallucinate and what are the trade-offs we should be looking for}. It presents a formal \textbf{impossibility theorem} demonstrating that no inference mechanism can simultaneously satisfy four fundamental properties: \textbf{truthful (non-hallucinatory) generation, semantic information conservation, relevant knowledge revelation, and knowledge-constrained optimality}. By modeling LLM inference as an \textbf{auction of ideas} where neural components compete to contribute to responses, we prove the impossibility using the Green-Laffont theorem. That mathematical framework provides a rigorous foundation for understanding the nature of inference process, with implications for model architecture, training objectives, and evaluation methods.

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

相关文章