Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.10321 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912896392364032 |
|---|---|
| author | Mukhopadhyay, Debayan Ghosh, Utshab Kumar Chatterjee, Shubham |
| author_facet | Mukhopadhyay, Debayan Ghosh, Utshab Kumar Chatterjee, Shubham |
| contents | Retrieving known items from vague descriptions, Tip-of-the-Tongue (ToT) retrieval, remains a significant challenge. We propose using a single call to a generic 8B-parameter LLM for query reformulation, bridging the gap between ill-formed ToT queries and specific information needs. This method is particularly effective where standard Pseudo-Relevance Feedback fails due to poor initial recall. Crucially, our LLM is not fine-tuned for ToT or specific domains, demonstrating that gains stem from our prompting strategy rather than model specialization. Rewritten queries feed a multi-stage pipeline: sparse retrieval (BM25), dense/late-interaction reranking (Contriever, E5-large-v2, ColBERTv2), monoT5 cross-encoding, and list-wise reranking (Qwen 2.5 72B). Experiments on 2025 TREC-ToT datasets show that while raw queries yield poor performance, our lightweight pre-retrieval transformation improves Recall by 20.61%. Subsequent reranking improves nDCG@10 by 33.88%, MRR by 29.92%, and MAP@10 by 29.98%, offering a cost-effective intervention that unlocks the potential of downstream rankers. Code and data: https://github.com/debayan1405/TREC-TOT-2025 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10321 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Single-Turn LLM Reformulation Powered Multi-Stage Hybrid Re-Ranking for Tip-of-the-Tongue Known-Item Retrieval Mukhopadhyay, Debayan Ghosh, Utshab Kumar Chatterjee, Shubham Information Retrieval Retrieving known items from vague descriptions, Tip-of-the-Tongue (ToT) retrieval, remains a significant challenge. We propose using a single call to a generic 8B-parameter LLM for query reformulation, bridging the gap between ill-formed ToT queries and specific information needs. This method is particularly effective where standard Pseudo-Relevance Feedback fails due to poor initial recall. Crucially, our LLM is not fine-tuned for ToT or specific domains, demonstrating that gains stem from our prompting strategy rather than model specialization. Rewritten queries feed a multi-stage pipeline: sparse retrieval (BM25), dense/late-interaction reranking (Contriever, E5-large-v2, ColBERTv2), monoT5 cross-encoding, and list-wise reranking (Qwen 2.5 72B). Experiments on 2025 TREC-ToT datasets show that while raw queries yield poor performance, our lightweight pre-retrieval transformation improves Recall by 20.61%. Subsequent reranking improves nDCG@10 by 33.88%, MRR by 29.92%, and MAP@10 by 29.98%, offering a cost-effective intervention that unlocks the potential of downstream rankers. Code and data: https://github.com/debayan1405/TREC-TOT-2025 |
| title | Single-Turn LLM Reformulation Powered Multi-Stage Hybrid Re-Ranking for Tip-of-the-Tongue Known-Item Retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2602.10321 |