序列级确定性降低知识 grounded 对话生成中的幻觉
Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation
AI总结：
本研究提出序列级确定性作为知识 grounded 对话生成幻觉的共性视角，设计两类基于确定性的回复排序方法，经多数据集、多解码方法和多模型实验验证可有效减少幻觉。
摘要：
在本研究中，我们提出序列级确定性作为知识 grounded 对话生成（KGDG）中幻觉问题的共性研究视角。我们探究了模型回复的幻觉程度与两类序列级确定性（概率确定性和语义确定性）之间的相关性。实证结果表明，模型回复中两类确定性的水平越高，幻觉程度越低。我们进一步提出了基于确定性的回复排序（CRR），这是一种解码阶段的幻觉缓解方法：先采样多个回复候选，再根据序列级确定性对其排序，输出确定性最高的回复。结合我们对序列级确定性的定义，我们设计了两类CRR方法：概率CRR（P-CRR）和语义CRR（S-CRR）。P-CRR使用整个序列的算术平均对数概率对单独采样的模型回复进行排序。S-CRR从语义空间角度进行确定性估计，基于由蕴含式一致性得分（AS）衡量的语义确定性水平对模型回复候选排序。通过在3个KGDG数据集、3种解码方法和4个KGDG模型上开展的大量实验，我们验证了CRR在KGDG任务中减少幻觉的有效性。
英文摘要：
In this work, we propose sequence-level certainty as a common theme over hallucination in Knowledge Grounded Dialogue Generation (KGDG). We explore the correlation between the level of hallucination in model responses and two types of sequence-level certainty: probabilistic certainty and semantic certainty. Empirical results reveal that higher levels of both types of certainty in model responses are correlated with lower levels of hallucination. We further propose Certainty-based Response Ranking (CRR), a decoding-time hallucination mitigation method that samples several response candidates, ranks them based on sequence-level certainty, and outputs the response with the highest certainty level. Aligning with our definitions of sequence-level certainty, we design 2 types of CRR approaches: Probabilistic CRR (P-CRR) and Semantic CRR (S-CRR). P-CRR ranks individually sampled model responses using the arithmetic mean log-probability of the entire sequence. S-CRR approaches certainty estimation from meaning-space, and ranks model response candidates based on their semantic certainty level as measured by an entailment-based Agreement Score (AS). Through extensive experiments across 3 KGDG datasets, 3 decoding methods, and 4 KGDG models, we validate the effectiveness of CRR for reducing hallucination in KGDG task.
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。
