Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Silva, Hugo, Mendes, Mateus, Oliveira, Hugo Gonçalo
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.17312
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908785562353664
author Silva, Hugo
Mendes, Mateus
Oliveira, Hugo Gonçalo
author_facet Silva, Hugo
Mendes, Mateus
Oliveira, Hugo Gonçalo
contents Large language models (LLMs) are evolving fast and are now frequently used as evaluators, in a process typically referred to as LLM-as-a-Judge, which provides quality assessments of model outputs. However, recent research points out significant vulnerabilities in such evaluation, including sensitivity to prompts, systematic biases, verbosity effects, and unreliable or hallucinated rationales. These limitations motivated the development of a more robust paradigm, dubbed LLM-as-a-Meta-Judge. This survey reviews recent advances in meta-judging and organizes the literature, by introducing a framework along six key perspectives: (i) Conceptual Foundations, (ii) Mechanisms of Meta-Judging, (iii) Alignment Training Methods, (iv) Evaluation, (v) Limitations and Failure Modes, and (vi) Future Directions. By analyzing the limitations of LLM-as-a-Judge and summarizing recent advances in meta-judging by LLMs, we argue that LLM-as-a-Meta-Judge offers a promising direction for more stable and trustworthy automated evaluation, while highlighting remaining challenges related to cost, prompt sensitivity, and shared model biases, which must be addressed to advance the next generation of LLM evaluation methodologies.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17312
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Meta-Judging with Large Language Models: Concepts, Methods, and Challenges
Silva, Hugo
Mendes, Mateus
Oliveira, Hugo Gonçalo
Computation and Language
Artificial Intelligence
Large language models (LLMs) are evolving fast and are now frequently used as evaluators, in a process typically referred to as LLM-as-a-Judge, which provides quality assessments of model outputs. However, recent research points out significant vulnerabilities in such evaluation, including sensitivity to prompts, systematic biases, verbosity effects, and unreliable or hallucinated rationales. These limitations motivated the development of a more robust paradigm, dubbed LLM-as-a-Meta-Judge. This survey reviews recent advances in meta-judging and organizes the literature, by introducing a framework along six key perspectives: (i) Conceptual Foundations, (ii) Mechanisms of Meta-Judging, (iii) Alignment Training Methods, (iv) Evaluation, (v) Limitations and Failure Modes, and (vi) Future Directions. By analyzing the limitations of LLM-as-a-Judge and summarizing recent advances in meta-judging by LLMs, we argue that LLM-as-a-Meta-Judge offers a promising direction for more stable and trustworthy automated evaluation, while highlighting remaining challenges related to cost, prompt sensitivity, and shared model biases, which must be addressed to advance the next generation of LLM evaluation methodologies.
title Meta-Judging with Large Language Models: Concepts, Methods, and Challenges
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.17312