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.
Cite
@article{arxiv.2506.22356,
title = {HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrieval},
author = {Kevin Duh and Eugene Yang and Orion Weller and Andrew Yates and Dawn Lawrie},
journal= {arXiv preprint arXiv:2506.22356},
year = {2025}
}