Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment
Pretrained language models (PLMs) based knowledge-grounded dialogue systems are prone to generate responses that are factually inconsistent with the provided knowledge source. In such inconsistent responses, the dialogue models fail to accurately express the external knowledge they rely upon. Inspired by previous work which identified that feed-forward networks (FFNs) within Transformers are responsible for factual knowledge expressions, we investigate two methods to efficiently improve the factual expression capability {of FFNs} by knowledge enhancement and alignment respectively. We first propose \textsc{K-Dial}, which {explicitly} introduces {extended FFNs in Transformers to enhance factual knowledge expressions} given the specific patterns of knowledge-grounded dialogue inputs. Additionally, we apply the reinforcement learning for factual consistency (RLFC) method to implicitly adjust FFNs' expressions in responses by aligning with gold knowledge for the factual consistency preference. To comprehensively assess the factual consistency and dialogue quality of responses, we employ extensive automatic measures and human evaluations including sophisticated fine-grained NLI-based metrics. Experimental results on WoW and CMU\_DoG datasets demonstrate that our methods efficiently enhance the ability of the FFN module to convey factual knowledge, validating the efficacy of improving factual consistency for knowledge-grounded dialogue systems.
Code (1)
Similar Papers 제목 키워드 기반
Q^{2}: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering
Neural knowledge-grounded generative models for dialogue often produce content that is factually inconsistent with the knowledge they rely on, making them unreliable and limiting their applicability. Inspired by recent w…
Abstractive Text SummarizationNatural Language InferenceQuestion AnsweringQuestion Generation+1$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering
Neural knowledge-grounded generative models for dialogue often produce content that is factually inconsistent with the knowledge they rely on, making them unreliable and limiting their applicability. Inspired by recent w…
Abstractive Text SummarizationDialogue EvaluationNatural Language InferenceQuestion Answering+2Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues
Implicit user feedback, user emotions and demographic information have shown to be promising sources for improving the accuracy and user engagement of responses generated by dialogue systems. However, the influence of su…
Building Knowledge-Grounded Dialogue Systems with Graph-Based Semantic Modeling
The knowledge-grounded dialogue task aims to generate responses that convey information from given knowledge documents. However, it is a challenge for the current sequence-based model to acquire knowledge from complex do…
Dialogue GenerationResponse GenerationText GenerationImproving Factuality for Dialogue Response Generation via Graph-Based Knowledge Augmentation
Large Language Models (LLMs) succeed in many natural language processing tasks. However, their tendency to hallucinate - generate plausible but inconsistent or factually incorrect text - can cause problems in certain tas…
Response Generation