PRISM：基于知识敏感对齐的概率重分配与跨句屏蔽
PRISM: Probability Reallocation with In-Span Masking for Knowledge-Sensitive Alignment
AI总结：
PRISM通过引入事实性风险标签和跨句依赖标注，改进监督微调以减少事实性错误。该方法通过概率重分配和模型感知门控，在关键事实位置调整学习，提升事实性指标同时保持能力平衡。
摘要：
监督微调（SFT）结合token级硬标签可能放大事实性不支持目标的过度模仿，导致多句生成中错误传播。我们研究了增强SFT设置，其中训练实例包含粗粒度句子级事实性风险标签和跨句依赖标注，提供关于事实承诺弱支持位置的结构化信号。我们提出PRISM，一种可微的风险门控框架，仅在事实关键位置修改学习。PRISM在标准SFT基础上增加了一个轻量级、模型感知的概率重分配目标，对高置信度的高风险目标token进行惩罚，其范围由span级风险权重和模型感知门控控制。在易产生幻觉的事实性基准和通用评估中，PRISM在多个模型架构上提升了事实性指标，同时保持了竞争性的整体能力轮廓。消融实验进一步显示，辅助信号在保守使用时最有效，且知识屏蔽与模型感知重分配在平衡事实修正和能力保持方面发挥互补作用。
英文摘要：
Supervised fine-tuning (SFT) with token-level hard labels can amplify overconfident imitation of factually unsupported targets, causing hallucinations that propagate in multi-sentence generation. We study an augmented SFT setting in which training instances include coarse sentence-level factuality risk labels and inter-sentence dependency annotations, providing structured signals about where factual commitments are weakly supported. We propose \textbf{PRISM}, a differentiable risk-gated framework that modifies learning only at fact-critical positions. PRISM augments standard SFT with a lightweight, model-aware probability reallocation objective that penalizes high-confidence predictions on risky target tokens, with its scope controlled by span-level risk weights and model-aware gating. Experiments on hallucination-sensitive factual benchmarks and general evaluations show that PRISM improves factual aggregates across backbones while maintaining a competitive overall capability profile. Ablations further show that the auxiliary signal is most effective when used conservatively, and that knowledge masking and model-aware reallocation play complementary roles in balancing factual correction and capability preservation.
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。
