NoVo：利用大语言模型中的注意力头进行范数投票以消除幻觉
NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
AI总结：
针对大语言模型幻觉问题，提出轻量级NoVo方法，通过仅需30个样本的推理算法选事实相关注意力头范数进行投票，在TruthfulQA MC1上超现有方法至少19个准确率点，泛化性优异且助力微调与对抗防御。
摘要：
大语言模型（LLM）中的幻觉问题仍是一大障碍，在事实准确性至关重要的高风险应用中尤为突出。尽管表示编辑和读取方法在减少幻觉方面取得了进展，但它们严重依赖专用工具并需在领域内样本上训练，这使其难以扩展且容易过拟合，限制了其准确性提升以及对不同数据集的泛化能力。本文提出了一种轻量级方法——范数投票（Norm Voting，NoVo），该方法挖掘注意力头范数尚未被利用的潜力，显著提升零样本多项选择题（MCQ）的事实准确性。NoVo首先通过一种仅需推理的高效算法自动选择与事实相关的头范数，该算法仅需30个随机样本，因此NoVo可轻松扩展到不同数据集。随后，所选的头范数被用于一种简单的投票算法，可大幅提升预测准确率。在TruthfulQA MC1数据集上，NoVo以至少19个准确率点的惊人优势超越了当前最先进水平及所有先前方法。NoVo在20个不同数据集上展现出出色的泛化能力，在超过90%的数据集上均有显著提升，远超当前所有表示编辑和读取方法。NoVo在微调策略和构建文本对抗防御方面也展现出良好的提升效果。NoVo利用头范数的有效性为LLM的可解释性、鲁棒性和可靠性开辟了新方向。
英文摘要：
Hallucinations in Large Language Models (LLMs) remain a major obstacle, particularly in high-stakes applications where factual accuracy is critical. While representation editing and reading methods have made strides in reducing hallucinations, their heavy reliance on specialised tools and training on in-domain samples, makes them difficult to scale and prone to overfitting. This limits their accuracy gains and generalizability to diverse datasets. This paper presents a lightweight method, Norm Voting (NoVo), which harnesses the untapped potential of attention head norms to dramatically enhance factual accuracy in zero-shot multiple-choice questions (MCQs). NoVo begins by automatically selecting truth-correlated head norms with an efficient, inference-only algorithm using only 30 random samples, allowing NoVo to effortlessly scale to diverse datasets. Afterwards, selected head norms are employed in a simple voting algorithm, which yields significant gains in prediction accuracy. On TruthfulQA MC1, NoVo surpasses the current state-of-the-art and all previous methods by an astounding margin -- at least 19 accuracy points. NoVo demonstrates exceptional generalization to 20 diverse datasets, with significant gains in over 90\% of them, far exceeding all current representation editing and reading methods. NoVo also reveals promising gains to finetuning strategies and building textual adversarial defence. NoVo's effectiveness with head norms opens new frontiers in LLM interpretability, robustness and reliability.
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。
