HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Duh, Kevin, Yang, Eugene, Weller, Orion, Yates, Andrew, Lawrie, Dawn
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