Streamlining Conformal Information Retrieval via Score Refinement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917793896595456 |
|---|---|
| author | Intrator, Yotam Kelner, Ori Cohen, Regev Goldenberg, Roman Rivlin, Ehud Freedman, Daniel |
| author_facet | Intrator, Yotam Kelner, Ori Cohen, Regev Goldenberg, Roman Rivlin, Ehud Freedman, Daniel |
| contents | Information retrieval (IR) methods, like retrieval augmented generation, are fundamental to modern applications but often lack statistical guarantees. Conformal prediction addresses this by retrieving sets guaranteed to include relevant information, yet existing approaches produce large-sized sets, incurring high computational costs and slow response times. In this work, we introduce a score refinement method that applies a simple monotone transformation to retrieval scores, leading to significantly smaller conformal sets while maintaining their statistical guarantees. Experiments on various BEIR benchmarks validate the effectiveness of our approach in producing compact sets containing relevant information. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02914 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Streamlining Conformal Information Retrieval via Score Refinement Intrator, Yotam Kelner, Ori Cohen, Regev Goldenberg, Roman Rivlin, Ehud Freedman, Daniel Information Retrieval Artificial Intelligence Machine Learning Information retrieval (IR) methods, like retrieval augmented generation, are fundamental to modern applications but often lack statistical guarantees. Conformal prediction addresses this by retrieving sets guaranteed to include relevant information, yet existing approaches produce large-sized sets, incurring high computational costs and slow response times. In this work, we introduce a score refinement method that applies a simple monotone transformation to retrieval scores, leading to significantly smaller conformal sets while maintaining their statistical guarantees. Experiments on various BEIR benchmarks validate the effectiveness of our approach in producing compact sets containing relevant information. |
| title | Streamlining Conformal Information Retrieval via Score Refinement |
| topic | Information Retrieval Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.02914 |