HLTCOE at TREC 2024 NeuCLIR Track

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Eugene, Lawrie, Dawn, Weller, Orion, Mayfield, James
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916981654945792
author Yang, Eugene
Lawrie, Dawn
Weller, Orion
Mayfield, James
author_facet Yang, Eugene
Lawrie, Dawn
Weller, Orion
Mayfield, James
contents The HLTCOE team applied PLAID, an mT5 reranker, GPT-4 reranker, score fusion, and document translation to the TREC 2024 NeuCLIR track. For PLAID we included a variety of models and training techniques -- Translate Distill (TD), Generate Distill (GD) and multi-lingual translate-distill (MTD). TD uses scores from the mT5 model over English MS MARCO query-document pairs to learn how to score query-document pairs where the documents are translated to match the CLIR setting. GD follows TD but uses passages from the collection and queries generated by an LLM for training examples. MTD uses MS MARCO translated into multiple languages, allowing experiments on how to batch the data during training. Finally, for report generation we experimented with system combination over different runs. One family of systems used either GPT-4o or Claude-3.5-Sonnet to summarize the retrieved results from a series of decomposed sub-questions. Another system took the output from those two models and verified/combined them with Claude-3.5-Sonnet. The other family used GPT4o and GPT3.5Turbo to extract and group relevant facts from the retrieved documents based on the decomposed queries. The resulting submissions directly concatenate the grouped facts to form the report and their documents of origin as the citations. The team submitted runs to all NeuCLIR tasks: CLIR and MLIR news tasks as well as the technical documents task and the report generation task.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00143
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HLTCOE at TREC 2024 NeuCLIR Track
Yang, Eugene
Lawrie, Dawn
Weller, Orion
Mayfield, James
Information Retrieval
The HLTCOE team applied PLAID, an mT5 reranker, GPT-4 reranker, score fusion, and document translation to the TREC 2024 NeuCLIR track. For PLAID we included a variety of models and training techniques -- Translate Distill (TD), Generate Distill (GD) and multi-lingual translate-distill (MTD). TD uses scores from the mT5 model over English MS MARCO query-document pairs to learn how to score query-document pairs where the documents are translated to match the CLIR setting. GD follows TD but uses passages from the collection and queries generated by an LLM for training examples. MTD uses MS MARCO translated into multiple languages, allowing experiments on how to batch the data during training. Finally, for report generation we experimented with system combination over different runs. One family of systems used either GPT-4o or Claude-3.5-Sonnet to summarize the retrieved results from a series of decomposed sub-questions. Another system took the output from those two models and verified/combined them with Claude-3.5-Sonnet. The other family used GPT4o and GPT3.5Turbo to extract and group relevant facts from the retrieved documents based on the decomposed queries. The resulting submissions directly concatenate the grouped facts to form the report and their documents of origin as the citations. The team submitted runs to all NeuCLIR tasks: CLIR and MLIR news tasks as well as the technical documents task and the report generation task.
title HLTCOE at TREC 2024 NeuCLIR Track
topic Information Retrieval
url https://arxiv.org/abs/2510.00143