相关论文: A Factuality and Diversity Reconciled Decoding Met…

The capability to generate responses with diversity and faithfulness using factual knowledge is paramount for creating a human-like, trustworthy dialogue system. Common strategies either adopt a two-step paradigm, which optimizes knowledge…

Despite the success of integrating large language models into the development of conversational systems, many studies have shown the effectiveness of retrieving and augmenting external knowledge for informative responses. Hence, many…

Dialogue generation has been successfully learned from scratch by neural networks, but tends to produce the same general response, e.g., "what are you talking about?", in many conversations. To reduce this homogeneity, external knowledge…

This study aims to generate responses based on real-world facts by conditioning context and external facts extracted from information websites. Our system is an ensemble system that combines three modules: generated-based module,…

The process of gathering ground truth data through human annotation is a major bottleneck in the use of information extraction methods for populating the Semantic Web. Crowdsourcing-based approaches are gaining popularity in the attempt to…

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 documents and…

Knowledge gaps and hallucinations are persistent challenges for Large Language Models (LLMs), which generate unreliable responses when lacking the necessary information to fulfill user instructions. Existing approaches, such as…

Background Based Conversations (BBCs) have been developed to make dialogue systems generate more informative and natural responses by leveraging background knowledge. Existing methods for BBCs can be grouped into two categories:…

Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…

Previous research on multi-party dialogue generation has predominantly leveraged structural information inherent in dialogues to directly inform the generation process. However, the prevalence of colloquial expressions and incomplete…

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…

Retrieval-Augmented Generation (RAG) has become an essential approach for extending the reasoning and knowledge capacity of large language models (LLMs). While prior research has primarily focused on retrieval quality and prompting…

Collecting data for training dialog systems can be extremely expensive due to the involvement of human participants and need for extensive annotation. Especially in document-grounded dialog systems, human experts need to carefully read the…

Recent neural models have shown significant progress in dialogue generation. Most generation models are based on language models. However, due to the Long Tail Phenomenon in linguistics, the trained models tend to generate words that appear…

To engage human users in meaningful conversation, open-domain dialogue agents are required to generate diverse and contextually coherent dialogue. Despite recent advancements, which can be attributed to the usage of pretrained language…

Open-domain response generation is the task of generating sensible and informative re-sponses to the source sentence. However, neural models tend to generate safe and mean-ingless responses. While cue-word introducing approaches encourage…

Many dialogue systems (DSs) lack characteristics humans have, such as emotion perception, factuality, and informativeness. Enhancing DSs with knowledge alleviates this problem, but, as many ways of doing so exist, keeping track of all…

Knowledge Graph(KG) grounded conversations often use large pre-trained models and usually suffer from fact hallucination. Frequently entities with no references in knowledge sources and conversation history are introduced into responses,…

Retrieval-augmented generation (RAG) is key to enhancing large language models (LLMs) to systematically access richer factual knowledge. Yet, using RAG brings intrinsic challenges, as LLMs must deal with potentially conflicting knowledge,…

Grounding responses in external knowledge represents an effective strategy for mitigating hallucinations in Large Language Models (LLMs). However, current LLMs struggle to seamlessly integrate knowledge while simultaneously maintaining…