Conversational search requires accurate interpretation of user intent from complex multi-turn
contexts. This paper presents ChatRetriever, which inherits the strong generalization …

As a cornerstone of modern information access, search engines have become
indispensable in everyday life. With the rapid advancements in AI and natural language …

Conversational search facilitates complex information retrieval by enabling multi-turn
interactions between users and the system. Supporting such interactions requires a …

We present a Conversational Chain-of-Action (Conv-CoA) framework for Open-domain
Conversational Question Answering (OCQA). Compared with literature, Conv-CoA …

In this paper, we study how open-source large language models (LLMs) can be effectively
deployed for improving query rewriting in conversational search, especially for ambiguous …

Conversational search supports multi-turn user-system interactions to solve complex
information needs. Different from the traditional single-turn ad-hoc search, conversational …

Conversational dense retrieval has shown to be effective in conversational search.
However, a major limitation of conversational dense retrieval is their lack of interpretability …

Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing
large language models (LLMs) through external knowledge retrieval. Despite its widespread …

The increasing size and complexity of pre-trained language models have demonstrated
superior performance in many applications, but they usually require large training datasets …

In this chapter, we discuss how to improve the GenIR systems based on user feedback.
Before describing the approaches, it is necessary to be aware that the concept of" user" has …