生成、判别、演化：通过细粒度句子级自演化增强上下文忠实度
Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution
AI总结：
提出GenDiE自演化框架，通过细粒度句子级生成与判别训练优化LLM上下文忠实度，在LFQA与反事实QA任务中超越基线并具备稳健领域适应能力。
摘要：
提升大型语言模型的上下文忠实度对于开发可信的检索增强生成系统并缓解幻觉至关重要，尤其是在长篇问答（LFQA）任务或涉及知识冲突的场景中。现有方法要么仅在推理时干预LLM而未解决其固有局限性，要么忽视了自我改进的潜力。本文提出GenDiE（Generate, Discriminate, Evolve），一种通过细粒度句子级优化增强上下文忠实度的新型自演化框架。GenDiE结合生成式与判别式训练，赋予LLM自生成与自评分能力以促进迭代自演化。这既支持用于模型对齐的数据构建，也支持推理期间的评分引导搜索。此外，通过将响应中的每个句子视为独立优化单元，GenDiE有效解决了以往方法在整体答案级优化的局限性，后者可能遗漏不忠实的细节。在ASQA（域内LFQA）和ConFiQA（域外反事实QA）数据集上的实验表明，GenDiE在忠实度与正确性上均超越多种基线，并展现出稳健的领域适应性能。
英文摘要：
Improving context faithfulness in large language models is essential for developing trustworthy retrieval augmented generation systems and mitigating hallucinations, especially in long-form question answering (LFQA) tasks or scenarios involving knowledge conflicts. Existing methods either intervene LLMs only at inference without addressing their inherent limitations or overlook the potential for self-improvement. In this paper, we introduce GenDiE (Generate, Discriminate, Evolve), a novel self-evolving framework that enhances context faithfulness through fine-grained sentence-level optimization. GenDiE combines both generative and discriminative training, equipping LLMs with self-generation and self-scoring capabilities to facilitate iterative self-evolution. This supports both data construction for model alignment and score-guided search during inference. Furthermore, by treating each sentence in a response as an independent optimization unit, GenDiE effectively addresses the limitations of previous approaches that optimize at the holistic answer level, which may miss unfaithful details. Experiments on ASQA (in-domain LFQA) and ConFiQA (out-of-domain counterfactual QA) datasets demonstrate that GenDiE surpasses various baselines in both faithfulness and correctness, and exhibits robust performance for domain adaptation.
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。
