The goal of information-seeking dialogue is to respond to seeker queries with natural
language utterances that are grounded on knowledge sources. However, dialogue systems …

Text generation has become more accessible than ever, and the increasing interest in these
systems, especially those using large language models, has spurred an increasing number …

Abstract Knowledge-grounded dialogue systems powered by large language models often
generate responses that, while fluent, are not attributable to a relevant source of information …

Charts are very popular to analyze data and convey important insights. People often analyze
visualizations to answer open-ended questions that require explanatory answers …

It has been shown that the interpretability of search results is enhanced when query aspects
covered by documents are explicitly provided. However, existing work on aspect-oriented …

Existing knowledge-grounded dialogue systems typically use finetuned versions of a
pretrained language model (LM) and large-scale knowledge bases. These models typically …

Maintaining faithfulness between responses and knowledge is an important research topic
for building reliable knowledge-grounded dialogue systems. Existing models heavily rely on …

State-of-the-art dialogue models still often stumble with regards to factual accuracy and self-
contradiction. Anecdotally, they have been observed to fail to maintain character identity …

While extreme-scale language models have demonstrated exceptional performance on a
variety of language tasks, the degree of control over these language models through pure …

In recent years, interest in vision-language tasks has grown, especially those involving chart
interactions. These tasks are inherently multimodal, requiring models to process chart …