真相感知上下文选择：缓解大语言模型被不真实上下文误导产生的幻觉
Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts
AI总结：
针对大语言模型易被不真实上下文误导产生幻觉的问题，提出轻量级真相感知上下文选择方法TACS，结合注意力掩码筛选真实上下文，还提出新评估指标，实验证明可有效提升误导场景下的响应质量。
摘要：
尽管大语言模型（LLMs）已展现出令人瞩目的文本生成能力，但它们很容易被用户或知识增强工具提供的不真实上下文误导，进而产生幻觉。为减轻LLMs被不真实上下文误导的问题，同时发挥知识增强的优势，我们提出了真相感知上下文选择（Truth-Aware Context Selection, TACS）——一种自适应识别并屏蔽输入中不真实上下文的轻量级方法。TACS首先利用LLM内部的参数化知识对输入上下文进行真相检测，随后根据每个位置的真实性构建对应的注意力掩码，筛选出真实上下文并丢弃不真实的部分。此外，我们提出了一种新的评估指标——干扰适应率（Disturbance Adaption Rate），用于进一步研究LLMs接受真实信息、抵御不真实信息的能力。实验结果表明，当存在误导性信息时，TACS能够有效过滤不真实上下文，并显著提升LLMs响应的整体质量。
英文摘要：
Although Large Language Models (LLMs) have demonstrated impressive text generation capabilities, they are easily misled by untruthful contexts provided by users or knowledge augmentation tools, leading to hallucinations. To alleviate LLMs from being misled by untruthful context and take advantage of knowledge augmentation, we propose Truth-Aware Context Selection (TACS), a lightweight method to adaptively recognize and mask untruthful context from the inputs. TACS begins by performing truth detection on the input context, leveraging the parameterized knowledge within the LLM. Subsequently, it constructs a corresponding attention mask based on the truthfulness of each position, selecting the truthful context and discarding the untruthful context. Additionally, we introduce a new evaluation metric, Disturbance Adaption Rate, to further study the LLMs' ability to accept truthful information and resist untruthful information. Experimental results indicate that TACS can effectively filter untruthful context and significantly improve the overall quality of LLMs' responses when presented with misleading information.
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。
