MétaCan
Menu
Back to cohort
Record W4412376941 · doi:10.1145/3726302.3730165

Assessing Support for the TREC 2024 RAG Track: A Large-Scale Comparative Study of LLM and Human Evaluations

2025· article· en· W4412376941 on OpenAlexafffund
Nandan Thakur, Ronak Pradeep, Shivani Upadhyay, Daniel Campos, Nick Craswell, Ian Soboroff, Hoa Trang Dang, Jimmy Lin

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsUniversity of Waterloo
FundersNatural Sciences and Engineering Research Council of CanadaNational Institute of Standards and Technology
KeywordsComputer scienceTrack (disk drive)Scale (ratio)Information retrievalArtificial intelligenceOperating systemCartographyGeography

Abstract

fetched live from OpenAlex

Retrieval-augmented generation (RAG) enables large language models (LLMs) to generate answers with citations from source documents containing ''ground truth''. A crucial factor in RAG evaluation is ''support'', or whether the information in the cited documents supports the answer. We conducted a comparative study of submissions to the TREC 2024 RAG Track, evaluating an automatic LLM judge (GPT-4o) against human judges for support assessment. We considered two conditions: (1) fully manual assessments from scratch and (2) manual assessments with post-editing of LLM predictions. Our results indicate good agreement between human and GPT-4o predictions. Further analysis of the disagreements shows that an independent human judge correlates better with GPT-4o than a human judge, suggesting that LLM judges can be a reliable alternative for support assessment. We provide a qualitative analysis of human and GPT-4o errors to help guide future evaluations.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.067
metaresearch head score (Gemma)0.239
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.067
Threshold uncertainty score0.356

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0670.239
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0060.003
Science and technology studies0.0020.002
Scholarly communication0.0040.003
Open science0.0020.003
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0030.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.054
GPT teacher head0.464
Teacher spread0.409 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes2
Has abstractyes

Explore more

Same topicRadiomics and Machine Learning in Medical ImagingFrench-language works237,207