A new research paper explores the variability in query expansion (QE) performance within information retrieval systems. The study proposes two complementary perspectives to explain these differences: the concept of an Ideal Expanded Query (IEQ) and a separability measure using Cohen's d. Experiments conducted on several TREC datasets indicate that expanded queries closer to the IEQ generally lead to better retrieval effectiveness, and the separability of relevant and non-relevant documents offers a valuable complementary insight into QE performance. AI
IMPACT Provides insights into improving retrieval effectiveness for LLM-based systems by understanding query expansion.
RANK_REASON Research paper published on arXiv detailing new methods for explaining query expansion performance in information retrieval.
Read on arXiv cs.IR (Information Retrieval) →
- BM25
- Ideal Expanded Query
- information retrieval
- large language models
- query expansion
- TREC DL 2019-2022
- TREC Robust
- alphaXiv
- arXiv
- CatalyzeX
- DagsHub
- Gotit.pub
- Hugging Face
- ScienceCast
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →