PICK：面向知识接地对话系统的精炼与知情候选评分
PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems
AI总结：
PICK框架通过重评分解码过程中产生的替代候选回复，在不增加标注数据和模型调优的情况下，提升知识接地对话系统回复的忠实性与相关性。
摘要：
将对话回复生成建立在外部知识之上，旨在产生信息丰富且引人入胜的回复。然而，当前的知识接地对话（KGD）系统常常由于幻觉和缺乏连贯性等问题，无法使生成的回复符合人类偏好的质量。在分析多个语言模型生成结果后，我们观察到在单一解码过程中存在替代生成回复。与解码过程优先选择的最优回复相比，这些替代回复更加忠实，并且与先前对话轮次的相关性相当或更高。为了应对这些挑战并基于这些观察，我们提出了精炼与知情候选评分（PICK），这是一种生成重评分框架，使模型能够生成忠实且相关的回复，而无需额外的标注数据或模型调优。通过全面的自动评估和人工评估，我们证明了PICK在生成更忠实回复的同时保持其与对话历史相关性的有效性。此外，PICK在所有解码策略中，无论是使用oracle知识还是检索知识，都能持续提升系统性能。我们在https://github.com/bryanwilie/pick中提供了详细实现。
英文摘要：
Grounding dialogue response generation on external knowledge is proposed to produce informative and engaging responses. However, current knowledge-grounded dialogue (KGD) systems often fail to align the generated responses with human-preferred qualities due to several issues like hallucination and the lack of coherence. Upon analyzing multiple language model generations, we observe the presence of alternative generated responses within a single decoding process. These alternative responses are more faithful and exhibit a comparable or higher level of relevance to prior conversational turns compared to the optimal responses prioritized by the decoding processes. To address these challenges and driven by these observations, we propose Polished \& Informed Candidate Scoring (PICK), a generation re-scoring framework that empowers models to generate faithful and relevant responses without requiring additional labeled data or model tuning. Through comprehensive automatic and human evaluations, we demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history. Furthermore, PICK consistently improves the system's performance with both oracle and retrieved knowledge in all decoding strategies. We provide the detailed implementation in https://github.com/bryanwilie/pick .
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。
