A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation
Grounding external knowledge can enhance the factuality of responses in dialogue generation. However, excessive emphasis on it might result in the lack of engaging and diverse expressions. Through the introduction of randomness in sampling, current approaches can increase the diversity. Nevertheless, such sampling method could undermine the factuality in dialogue generation. In this study, to discover a solution for advancing creativity without relying on questionable randomness and to subtly reconcile the factuality and diversity within the source-grounded paradigm, a novel method named DoGe is proposed. DoGe can dynamically alternate between the utilization of internal parameter knowledge and external source knowledge based on the model's factual confidence. Extensive experiments on three widely-used datasets show that DoGe can not only enhance response diversity but also maintain factuality, and it significantly surpasses other various decoding strategy baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Dialogue GenerationDiversitySimilar Papers 제목 키워드 기반
REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy
Decoding methods for large language models (LLMs) usually struggle with the tradeoff between ensuring factuality and maintaining diversity. For example, a higher p threshold in the nucleus (top-p) sampling increases the …
DiversityHallucinationControllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model
In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes theorem. One component is a traditional ungrounded response generation model …
Response GenerationEntropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination -- generating content ungrounded in the realities of training data. Recent work has focused on decoding techniqu…
HallucinationWatermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding
Large Vision-Language Models (LVLMs) have recently shown promising results on various multimodal tasks, even achieving human-comparable performance in certain cases. Nevertheless, LVLMs remain prone to hallucinations -- …
FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge
Evaluating the factual consistency of automatically generated summaries is essential for the progress and adoption of reliable summarization systems. Despite recent advances, existing factuality evaluation models are not…
News Summarization