Truth Forest：通过无需微调的干预实现大语言模型的多尺度真实性
Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
AI总结：
本文提出无需微调的 Truth Forest，利用多维正交探针和 Random Peek 干预 LLM 内部真实性表征，显著提升 Llama-2-7B 及微调模型在 TruthfulQA 上的真实性。
摘要：
尽管大语言模型（LLM）在各类任务中取得了巨大成功，但它们仍会产生幻觉。我们提出 Truth Forest，该方法通过利用多维正交探针揭示隐藏的真实性表征来增强 LLM 的真实性。具体而言，它通过在探针中引入正交约束，创建多个用于建模真实性的正交基。此外，我们提出 Random Peek，这是一种系统性技术，会考虑序列内更大范围的位置，从而缩小 LLM 中识别真实性特征与生成真实性特征之间的差距。借助该方法，我们在 TruthfulQA 上将 Llama-2-7B 的真实性从 40.8% 提升至 74.5%。同样，在经过微调的模型中也观察到显著提升。我们使用探针对真实性特征进行了全面分析。可视化结果表明，正交探针捕获了互补的真实性相关特征，形成边界清晰的簇，揭示了数据集的内在结构。
英文摘要：
Despite the great success of large language models (LLMs) in various tasks, they suffer from generating hallucinations. We introduce Truth Forest, a method that enhances truthfulness in LLMs by uncovering hidden truth representations using multi-dimensional orthogonal probes. Specifically, it creates multiple orthogonal bases for modeling truth by incorporating orthogonal constraints into the probes. Moreover, we introduce Random Peek, a systematic technique considering an extended range of positions within the sequence, reducing the gap between discerning and generating truth features in LLMs. By employing this approach, we improved the truthfulness of Llama-2-7B from 40.8\% to 74.5\% on TruthfulQA. Likewise, significant improvements are observed in fine-tuned models. We conducted a thorough analysis of truth features using probes. Our visualization results show that orthogonal probes capture complementary truth-related features, forming well-defined clusters that reveal the inherent structure of the dataset.
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。
