Bibliographic Details
| Title: |
Probing subjective judgment variance in LLM evaluators: A framework for robust IR evaluation. |
| Authors: |
Kumar, Ritesh1 (AUTHOR) riteshkumar@iiitsurat.ac.in |
| Source: |
Applied Intelligence. Apr2026, Vol. 56 Issue 6, p1-22. 22p. |
| Abstract: |
Large Language Models (LLMs) are increasingly used as evaluators for subjective Information Retrieval (IR) tasks, yet their reliability under ambiguity remains poorly understood. We systematically probe LLM-as-a-judge systems by deliberately maximizing inter-model disagreement, which we formalize as horizontal variance. Across five widely used LLM evaluators, we observe that ambiguity-based prompts induce up to a 63% increase in horizontal variance, while intra-model (vertical) variance remains stable. This indicates systematic, not random, evaluator inconsistency. Our results show that models may appear stable in isolation yet diverge substantially when evaluated collectively, exposing hidden bias and instability. These findings highlight the risks of naive deployment of LLM evaluators in fairness-sensitive IR pipelines and motivate multi-model, variance-aware evaluation strategies. [ABSTRACT FROM AUTHOR] |
|
Copyright of Applied Intelligence is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Engineering Source |
