让大模型在单文本下也能准确识别自己写的文字
From Implicit to Explicit: Enhancing Self-Recognition in Large Language Models
- 提出认知手术框架，解决模型自我识别能力在单文本下的失效问题
- 在单文本场景下使三款模型自识别准确率分别达99%、97.69%、97.13%
- 适合关注模型可解释性与自我认知机制的研究者
大语言模型具备一定的自我识别能力，可在成对文本对比中判断哪篇是自己生成的。然而在单个文本呈现的场景下，性能急剧下降。本文发现该现象源于隐式自我识别（ISR）：模型虽在特征空间中编码了自识别信息，但输出行为仍无法有效反映。为此，提出认知手术（CoSur）框架，包含表征提取、子空间构建、作者身份判别和认知编辑四个模块。实验表明，该方法显著提升了三款不同LLM在单文本场景下的自识别能力，平均准确率分别达到99.00%、97.69%和97.13%。
原文摘要 · Abstract (English)
Large language models (LLMs) have been shown to possess a degree of self-recognition ability, which used to identify whether a given text was generated by themselves. Prior work has demonstrated that this capability is reliably expressed under the pair presentation paradigm (PPP), where the model is presented with two texts and asked to choose which one it authored. However, performance deteriorates sharply under the individual presentation paradigm (IPP), where the model is given a single text to judge authorship. Although this phenomenon has been observed, its underlying causes have not been systematically analyzed. In this paper, we first investigate the cause of this failure and attribute it to implicit self-recognition (ISR). ISR describes the gap between internal representations and output behavior in LLMs: under the IPP scenario, the model encodes self-recognition information in its feature space, yet its ability to recognize self-generated texts remains poor. To mitigate the ISR of LLMs, we propose cognitive surgery (CoSur), a novel framework comprising four main modules: representation extraction, subspace construction, authorship discrimination, and cognitive editing. Experimental results demonstrate that our proposed method improves the self-recognition performance of three different LLMs in the IPP scenario, achieving average accuracies of 99.00%, 97.69%, and 97.13%, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。