通过诱导幻觉缓解大语言模型的幻觉问题
Alleviating Hallucinations of Large Language Models through Induced Hallucinations
AI总结：
针对大语言模型的幻觉问题，提出“诱导-对比”解码策略，通过构建弱事实性模型并在解码时惩罚诱导幻觉，有效提升多类模型的事实准确性，部分小模型性能可对标ChatGPT、GPT4。
摘要：
尽管大语言模型（LLMs）能力出众，但已观察到它们生成的回复中包含不准确或捏造的信息，这一现象通常被称为“幻觉”。本研究提出一种简单的“诱导-对比”解码（ICD）策略以缓解幻觉问题。我们首先通过从原始LLMs中诱导幻觉，构建一个事实性较弱的LLM。随后，我们在解码过程中对这些诱导出的幻觉施加惩罚，以提升生成内容的事实准确性。具体而言，我们通过对比解码，放大原始模型的预测结果，同时压低诱导出的非真实预测结果，以此确定最终的下一词元预测。在基于判别和基于生成的幻觉评估基准（如TruthfulQA和FActScore）上的实验结果表明，我们提出的ICD方法能够在不同模型规模和模型家族中有效提升LLMs的事实准确性。例如，搭载ICD后，Llama2-7B-Chat和Mistral-7B-Instruct在TruthfulQA上分别取得了与ChatGPT和GPT4相当的性能。
英文摘要：
Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as ``hallucination''. In this work, we propose a simple \textit{Induce-then-Contrast} Decoding (ICD) strategy to alleviate hallucinations. We first construct a factually weak LLM by inducing hallucinations from the original LLMs. Then, we penalize these induced hallucinations during decoding to enhance the factuality of the generated content. Concretely, we determine the final next-token predictions by amplifying the predictions from the original model and downplaying the induced untruthful predictions via contrastive decoding. Experimental results on both discrimination-based and generation-based hallucination evaluation benchmarks, such as TruthfulQA and \textsc{FActScore}, demonstrate that our proposed ICD methods can effectively enhance the factuality of LLMs across various model sizes and families. For example, when equipped with ICD, Llama2-7B-Chat and Mistral-7B-Instruct achieve performance comparable to ChatGPT and GPT4 on TruthfulQA, respectively.
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。
