Saved in:
Bibliographic Details
Main Authors: Chen, Junjie, Dong, Yuxi, Li, Haitao, Su, Weihang, Zhou, Yujia, Zhang, Min, Liu, Yiqun, Ai, Qinyao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2606.01629
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917553479090176
author Chen, Junjie
Dong, Yuxi
Li, Haitao
Su, Weihang
Zhou, Yujia
Zhang, Min
Liu, Yiqun
Ai, Qinyao
author_facet Chen, Junjie
Dong, Yuxi
Li, Haitao
Su, Weihang
Zhou, Yujia
Zhang, Min
Liu, Yiqun
Ai, Qinyao
contents As large language models (LLMs) are increasingly used for long-form generation, reliably evaluating long-form outputs has become a critical challenge. LLM-as-a-judge offers a scalable alternative to human evaluation, yet its reliability in long-form output evaluation remains underexamined: existing meta-evaluation benchmarks focus mainly on short-form outputs. Compared with short-form evaluation, long-form evaluation is not merely a matter of output length; it often requires judges to handle more complex document-level demands. In this work, we introduce LongJudgeBench, a comprehensive benchmark for evaluating LLM judges on long-form outputs across diverse real-world scenarios and judging protocols. We systematically evaluate a broad range of LLM judges, covering multiple base models and judging settings. Our results reveal a substantial reliability gap: current LLM judges remain unstable across scenarios, and rubrics or references are helpful but not always sufficient. We hope LongJudgeBench will support future research on more robust, context-aware, and human-aligned LLM-as-a-judge methods. Our code is available at https://anonymous.4open.science/r/LongJudgeBench-F782.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01629
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation
Chen, Junjie
Dong, Yuxi
Li, Haitao
Su, Weihang
Zhou, Yujia
Zhang, Min
Liu, Yiqun
Ai, Qinyao
Computation and Language
As large language models (LLMs) are increasingly used for long-form generation, reliably evaluating long-form outputs has become a critical challenge. LLM-as-a-judge offers a scalable alternative to human evaluation, yet its reliability in long-form output evaluation remains underexamined: existing meta-evaluation benchmarks focus mainly on short-form outputs. Compared with short-form evaluation, long-form evaluation is not merely a matter of output length; it often requires judges to handle more complex document-level demands. In this work, we introduce LongJudgeBench, a comprehensive benchmark for evaluating LLM judges on long-form outputs across diverse real-world scenarios and judging protocols. We systematically evaluate a broad range of LLM judges, covering multiple base models and judging settings. Our results reveal a substantial reliability gap: current LLM judges remain unstable across scenarios, and rubrics or references are helpful but not always sufficient. We hope LongJudgeBench will support future research on more robust, context-aware, and human-aligned LLM-as-a-judge methods. Our code is available at https://anonymous.4open.science/r/LongJudgeBench-F782.
title Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation
topic Computation and Language
url https://arxiv.org/abs/2606.01629