HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrieval
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_ | 1866909663106170880 |
|---|---|
| author | Duh, Kevin Yang, Eugene Weller, Orion Yates, Andrew Lawrie, Dawn |
| author_facet | Duh, Kevin Yang, Eugene Weller, Orion Yates, Andrew Lawrie, Dawn |
| contents | The HLTCOE LiveRAG submission utilized the GPT-researcher framework for researching the context of the question, filtering the returned results, and generating the final answer. The retrieval system was a ColBERT bi-encoder architecture, which represents a passage with many dense tokens. Retrieval used a local, compressed index of the FineWeb10-BT collection created with PLAID-X, using a model fine-tuned for multilingual retrieval. Query generation from context was done with Qwen2.5-7B-Instruct, while filtering was accomplished with m2-bert-80M-8k-retrieval. Up to nine passages were used as context to generate an answer using Falcon3-10B. This system placed 5th in the LiveRAG automatic evaluation for correctness with a score of 1.07. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22356 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrieval Duh, Kevin Yang, Eugene Weller, Orion Yates, Andrew Lawrie, Dawn Information Retrieval The HLTCOE LiveRAG submission utilized the GPT-researcher framework for researching the context of the question, filtering the returned results, and generating the final answer. The retrieval system was a ColBERT bi-encoder architecture, which represents a passage with many dense tokens. Retrieval used a local, compressed index of the FineWeb10-BT collection created with PLAID-X, using a model fine-tuned for multilingual retrieval. Query generation from context was done with Qwen2.5-7B-Instruct, while filtering was accomplished with m2-bert-80M-8k-retrieval. Up to nine passages were used as context to generate an answer using Falcon3-10B. This system placed 5th in the LiveRAG automatic evaluation for correctness with a score of 1.07. |
| title | HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2506.22356 |