熵引导的外推解码提升大语言模型的事实性
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
AI总结：
针对大语言模型的幻觉问题，提出基于熵引导低层选择的外推解码方法，通过外推最后层后关键token概率、解耦低层选择与最终层，在多数据集上大幅超越现有最优解码方法。
摘要：
大语言模型（LLMs）展现出出色的自然语言能力，但存在幻觉问题——生成的内容缺乏训练数据中的现实依据。近期研究聚焦于解码技术，在推理阶段利用LLMs对事实知识的层级化表示，通过调整推理时的预测分布来提升事实性。当前最优方法通过对比低层的早退出分布与最终层分布来优化解码，以利用模型前向传播过程中与事实性相关的信息。但这类方法通常假设最终层最可靠，且低层选择过程依赖于最终层。本研究首先提出对最后一层之后的关键token概率进行外推，以实现更精准的对比；此外还采用逐层熵引导的低层选择机制，将选择过程与最终层解耦。实验结果显示该方法性能优异，在多个不同数据集上以大幅优势超越现有最优水平。分析表明，不同类型的提示词适配不同的选择策略。
英文摘要：
Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination -- generating content ungrounded in the realities of training data. Recent work has focused on decoding techniques to improve factuality during inference by leveraging LLMs' hierarchical representation of factual knowledge, manipulating the predicted distributions at inference time. Current state-of-the-art approaches refine decoding by contrasting early-exit distributions from a lower layer with the final layer to exploit information related to factuality within the model forward procedure. However, such methods often assume the final layer is the most reliable and the lower layer selection process depends on it. In this work, we first propose extrapolation of critical token probabilities beyond the last layer for more accurate contrasting. We additionally employ layer-wise entropy-guided lower layer selection, decoupling the selection process from the final layer. Experiments demonstrate strong performance - surpassing state-of-the-art on multiple different datasets by large margins. Analyses show different kinds of prompts respond to different selection strategies.
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。
