Structured and Natural Responses Co-generation for Conversational Search
Paper · Source
Synthesis notes from this paper's topics
This paper has no direct semantic matches yet — here are notes from the topic(s) it's filed under.
- Why do users drift away from their original information need?
- Can generative and discriminative models reach agreement?
- How do logic units preserve procedural coherence better than chunks?
- What makes strategic question-asking succeed or fail?
- Can reference resolution work as a language modeling problem?
- Can AI systems detect and correct misunderstandings after responding?
- Does training on messy search processes improve reasoning?
- How can models select the most informative question to ask?