A new paper from arXiv explores the balance between query fidelity and retrieval breadth in conversational search systems. Researchers evaluated five query-generation configurations using BM25 and SPLADE retrieval within a behavior-adaptive assistant at the iKAT SCAI 2026 setting. The findings suggest that while combining a minimal-faithful resolver with a learned rewriter can improve retrieval scores, it may not necessarily lead to higher conversational satisfaction, highlighting the need to separate query interpretation from retrieval expansion. AI
IMPACT This research could lead to more intuitive and effective conversational search agents by better balancing information retrieval breadth with user intent.
RANK_REASON The item is an academic paper submitted to arXiv detailing research on conversational search. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
- alphaXiv
- arXiv
- BM25
- CatalyzeX Code Finder for Papers
- Connected Papers
- CORE Recommender
- DagsHub
- Gotit.pub
- Hugging Face
- iKAT SCAI 2026
- Influence Flower
- Litmaps
- ScienceCast
- scite Smart Citations
- SPLADE
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →