The DOI matches its Crossref record; the references it cites are not checked yet.
Don't Use LLMs to Make Relevance Judgments
Open accessAbstract
Relevance judgments and other truth data for information retrieval (IR) evaluations are created manually. There is a strong temptation to use large language models (LLMs) as proxies for human judges. However, letting the LLM write your truth data handicaps the evaluation by setting that LLM as a ceiling on performance. There are ways to use LLMs in the relevance assessment process, but just generating relevance judgments with a prompt isn’t one of them.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
The citation lists haven’t been fetched yet
Cited by 33
Metadata
- Authors
- Soboroff, I.
- Affiliations
- National Institute of Standards and Technology (US)
- Corresponding author
- Soboroff, Ian
- ORCID
- Soboroff, Ian
- Venue
- Information Retrieval Research
- Publisher
- Radboud University
- Published
- 2025-03-25
- Volume
- 1
- Issue
- 1
- Pages
- 29-46
- ISSN
- 3050-9106 (ISSN-L)
- 3050-9114
- PMC
- PMC11984504
- OpenAlex
- W4408811965
- Cited by
- 33
- References
- 0
- Citations by year
- 2026: 14 · 2025: 19
- FWCI
- 21.21
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Information Retrieval Research (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- National Institute of Standards and Technology
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Keywords
- large language models, relevance assessment, information retrieval evaluation, human judges, evaluation bias, ceiling effect
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
