pith. sign in

arxiv: 2409.15133 · v2 · pith:QIZ6RJDEnew · submitted 2024-09-23 · 💻 cs.IR

Don't Use LLMs to Make Relevance Judgments

Ian Soboroff This is my paper
classification 💻 cs.IR
keywords judgmentsrelevancearxivcollectioncontractorskeynotelanguagellms
0
0 comments X
read the original abstract

Making the relevance judgments for a TREC-style test collection can be complex and expensive. A typical TREC track usually involves a team of six contractors working for 2-4 weeks. Those contractors need to be trained and monitored. Software has to be written to support recording relevance judgments correctly and efficiently. The recent advent of large language models that produce astoundingly human-like flowing text output in response to a natural language prompt has inspired IR researchers to wonder how those models might be used in the relevance judgment collection process. At the ACM SIGIR 2024 conference, a workshop ``LLM4Eval'' provided a venue for this work, and featured a data challenge activity where participants reproduced TREC deep learning track judgments, as was done by Thomas et al (arXiv:2408.08896, arXiv:2309.10621). I was asked to give a keynote at the workshop, and this paper presents that keynote in article form. The bottom-line-up-front message is, don't use LLMs to create relevance judgments for TREC-style evaluations.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Evaluating Tool-Using Language Agents: Judge Reliability, Propagation Cascades, and Runtime Mitigation in AgentProp-Bench

    cs.AI 2026-04 conditional novelty 7.0

    AgentProp-Bench shows substring judging agrees with humans at kappa=0.049, LLM ensemble at 0.432, bad-parameter injection propagates with ~0.62 probability, rejection and recovery are independent, and a runtime fix cu...

  2. Hybrid Pooling with LLMs via Relevance Context Learning

    cs.IR 2026-02 unverdicted novelty 7.0

    Relevance Context Learning generates explicit relevance narratives from judged examples to guide LLM assessors, outperforming zero-shot and standard in-context learning for IR relevance judgments.

  3. LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods

    cs.CL 2024-12 accept novelty 3.0

    A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.