Related papers: N-best Response-based Analysis of Contradiction-aw…
Mitigating the generation of contradictory responses poses a substantial challenge in dialogue response generation. The quality and quantity of available contradictory response data play a vital role in suppressing these contradictions,…
Despite significant progress in neural abstractive summarization, recent studies have shown that the current models are prone to generating summaries that are unfaithful to the original context. To address the issue, we study contrast…
Open-domain dialogue generation suffers from the data insufficiency problem due to the vast size of potential responses. In this paper, we propose to explore potential responses by counterfactual reasoning. Given an observed response, the…
Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make…
We introduce a novel data generation method for contradiction detection, which leverages the generative power of large language models as well as linguistic rules. Our vision is to provide a condensed corpus of prototypical contradictions,…
End-to-end neural models for intelligent dialogue systems suffer from the problem of generating uninformative responses. Various methods were proposed to generate more informative responses by leveraging external knowledge. However, few…
How do language models use contextual information to answer health questions? How are their responses impacted by conflicting contexts? We assess the ability of language models to reason over long, conflicting biomedical contexts using…
Recent advances in sequence-to-sequence learning reveal a purely data-driven approach to the response generation task. Despite its diverse applications, existing neural models are prone to producing short and generic replies, making it…
The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to…
Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…
Recent progress on neural approaches for language processing has triggered a resurgence of interest on building intelligent open-domain chatbots. However, even the state-of-the-art neural chatbots cannot produce satisfying responses for…
Neural conversational models learn to generate responses by taking into account the dialog history. These models are typically optimized over the query-response pairs with a maximum likelihood estimation objective. However, the…
With the rapid development of artificial intelligence technology, especially the increasingly widespread application of question-and-answer systems, high-quality question generation has become a key component in supporting the development…
Automated reasoning with unstructured natural text is a key requirement for many potential applications of NLP and for developing robust AI systems. Recently, Language Models (LMs) have demonstrated complex reasoning capacities even without…
Neural approaches to Natural Language Generation (NLG) have been promising for goal-oriented dialogue. One of the challenges of productionizing these approaches, however, is the ability to control response quality, and ensure that generated…
Retrieval Augmented Generation (RAG) systems have emerged as a powerful method for enhancing large language models (LLMs) with up-to-date information. However, the retrieval step in RAG can sometimes surface documents containing…
Conversational recommender systems have attracted immense attention recently. The most recent approaches rely on neural models trained on recorded dialogs between humans, implementing an end-to-end learning process. These systems are…
In open-domain conversational systems, it is important but challenging to leverage background knowledge. We can use the incorporation of knowledge to make the generation of dialogue controllable, and can generate more diverse sentences that…
Most language models currently available are prone to self-contradiction during dialogues. To mitigate this issue, this study explores a novel contradictory dialogue processing task that aims to detect and modify contradictory statements in…
This work examines the use of contradiction in natural language inference (NLI) for question answering (QA). Typically, NLI systems help answer questions by determining if a potential answer is \emph{entailed} (supported) by some background…