TREC 2025 Proceedings

Submission Details

Organization

UvA

Track

RAG TREC Instrument for Multilingual Evaluation

Task

Report Generation Task

Date

2025-08-26

Run Description

Document collection

['English subset']

Machine translation of documents

['None']

Write a short description of your retrieval process

sets of document get read by llm as a judge which extracts factsoids.

Write a short description of your generation process

multi agent pipeline which searches and merges information into a final report. no postprocessing

Which LLM(s) where used by your system?

gpt-4o-mini, gpt-4.1-mini and gpt-4.1

Open repository link

none

Assessing priority

1 (highest)

Evaluation Files

• zetaalpha.autoargue (autoargue)
• zetaalpha.almost-human-judgments.tsv (almost-human-judgments.tsv)
• zetaalpha.almost-human-scores.tsv (almost-human-scores.tsv)
• zetaalpha.autoargue-scores.tsv (autoargue-scores.tsv)
• zetaalpha.autoargue-judgments.jsonl (autoargue-judgments.jsonl)

Paper