通过动态校准提升大模型事实准确性，防止幻觉生成。
DSCC-HS: A Dynamic Self-Reinforcing Framework for Hallucination Suppression in Large Language Models
- 用两个代理模型实时生成纠偏信号，动态修正生成过程。
- 在TruthfulQA上达99.2%事实一致性，在BioGEN上获46.50最高得分。
- 无需修改原模型，可直接接入，适合追求高可信度的部署场景。
大语言模型的幻觉问题严重阻碍其可靠应用。现有方法如检索增强生成（RAG）多为被动响应。本文提出动态自强化幻觉抑制框架（DSCC-HS），在自回归解码过程中主动干预。受双过程认知理论启发，DSCC-HS采用一个轻量级代理模型，以事实对齐代理（FAP）和幻觉检测代理（HDP）双重角色训练。推理时，这两个代理在每一步生成决策差异向量（即FAP与HDP logits之差），作为实时校正信号注入目标模型。该方法无需修改目标模型，具备即插即用特性。在TruthfulQA和BioGEN上的实验表明，DSCC-HS达到当前最优性能：在TruthfulQA上实现99.2%的事实一致性率（FCR），在长文本生成基准BioGEN上取得46.50的最高事实得分（FactScore）。结果验证了该框架在提升大模型事实性方面的有效性与普适性。
原文摘要 · Abstract (English)
Large Language Model (LLM) hallucination is a significant barrier to their reliable deployment. Current methods like Retrieval-Augmented Generation (RAG) are often reactive. We introduce **Dynamic Self-reinforcing Calibration for Hallucination Suppression (DSCC-HS)**, a novel, proactive framework that intervenes during autoregressive decoding. Inspired by dual-process cognitive theory, DSCC-HS uses a compact proxy model, trained in adversarial roles as a Factual Alignment Proxy (FAP) and a Hallucination Detection Proxy (HDP). During inference, these proxies dynamically steer a large target model by injecting a real-time steering vector, which is the difference between FAP and HDP logits, at each decoding step. This plug-and-play approach requires no modification to the target model. Our experiments on TruthfulQA and BioGEN show DSCC-HS achieves state-of-the-art performance. On TruthfulQA, it reached a 99.2% Factual Consistency Rate (FCR). On the long-form BioGEN benchmark, it attained the highest FActScore of 46.50. These results validate DSCC-HS as a principled and efficient solution for enhancing LLM factuality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。