让大模型自动生成精准句子级引用，无需人工标注
SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
- 利用模型自身判断引用必要性，通过上下文删减生成奖励信号
- 在五个长文本问答任务上，引用准确率提升5.3点
- 适合需要高可信度引用的学术写作与信息检索场景
我们提出SelfCite，一种新型自监督方法，使大语言模型能够生成高质量、细粒度的句子级引用。该方法不依赖昂贵的人工标注，而是利用模型自身提供的奖励信号：若某引用必要，则移除对应上下文内容将导致相同回复无法生成；若引用充分，则仅保留引用内容仍可维持原回复。该奖励信号可用于推理阶段的best-of-N采样以提升引用质量，也可用于偏好优化直接微调模型。在LongBench-Cite基准上，五个长文本问答任务的引用F1值最高提升5.3分。代码已开源。
原文摘要 · Abstract (English)
We introduce SelfCite, a novel self-supervised approach that aligns LLMs to generate high-quality, fine-grained, sentence-level citations for the statements in their generated responses. Instead of only relying on costly and labor-intensive annotations, SelfCite leverages a reward signal provided by the LLM itself through context ablation: If a citation is necessary, removing the cited text from the context should prevent the same response; if sufficient, retaining the cited text alone should preserve the same response. This reward can guide the inference-time best-of-N sampling strategy to improve citation quality significantly, as well as be used in preference optimization to directly fine-tune the models for generating better citations. The effectiveness of SelfCite is demonstrated by increasing citation F1 up to 5.3 points on the LongBench-Cite benchmark across five long-form question answering tasks. The source code is available at https://github.com/facebookresearch/SelfCite
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。