HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912568841338880 |
|---|---|
| author | Santra, Payel Ghosh, Madhusudan Ganguly, Debasis Basuchowdhuri, Partha Naskar, Sudip Kumar |
| author_facet | Santra, Payel Ghosh, Madhusudan Ganguly, Debasis Basuchowdhuri, Partha Naskar, Sudip Kumar |
| contents | Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). However, effectively combining evidence from these heterogeneous sources is challenging as the respective similarity scores are not inter-comparable. Additionally, aggregating beliefs from the outputs of multiple rankers can improve the effectiveness of RAG. Our proposed method first aggregates the top-documents from a number of IR models using a standard rank fusion technique for each source (labeled and unlabeled). Next, we standardize the retrieval score distributions within each source by applying z-score transformation before merging the top-retrieved documents from the two sources. We evaluate our approach on the fact verification task, demonstrating that it consistently improves over the best-performing individual ranker or source and also shows better out-of-domain generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02837 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers Santra, Payel Ghosh, Madhusudan Ganguly, Debasis Basuchowdhuri, Partha Naskar, Sudip Kumar Information Retrieval Artificial Intelligence Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). However, effectively combining evidence from these heterogeneous sources is challenging as the respective similarity scores are not inter-comparable. Additionally, aggregating beliefs from the outputs of multiple rankers can improve the effectiveness of RAG. Our proposed method first aggregates the top-documents from a number of IR models using a standard rank fusion technique for each source (labeled and unlabeled). Next, we standardize the retrieval score distributions within each source by applying z-score transformation before merging the top-retrieved documents from the two sources. We evaluate our approach on the fact verification task, demonstrating that it consistently improves over the best-performing individual ranker or source and also shows better out-of-domain generalization. |
| title | HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2509.02837 |