Saved in:
Bibliographic Details
Main Authors: Chirkova, Nadezhda, Ajayi, Tunde Oluwaseyi, Aycock, Seth, Mujahid, Zain Muhammad, Perlić, Vladana, Borisova, Ekaterina, Vartampetian, Markarit
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.09147
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917157674156032
author Chirkova, Nadezhda
Ajayi, Tunde Oluwaseyi
Aycock, Seth
Mujahid, Zain Muhammad
Perlić, Vladana
Borisova, Ekaterina
Vartampetian, Markarit
author_facet Chirkova, Nadezhda
Ajayi, Tunde Oluwaseyi
Aycock, Seth
Mujahid, Zain Muhammad
Perlić, Vladana
Borisova, Ekaterina
Vartampetian, Markarit
contents Prompting large language models (LLMs) to evaluate generated text, known as LLM-as-a-judge, has become a standard evaluation approach in natural language generation (NLG), but is primarily used as a quantitative tool, i.e. with numerical scores as main outputs. In this work, we propose LLM-as-a-qualitative-judge, an LLM-based evaluation approach with the main output being a structured report of common issue types in the NLG system outputs. Our approach is targeted at providing developers with meaningful insights on what improvements can be done to a given NLG system and consists of two main steps, namely open-ended per-instance issue analysis and clustering of the discovered issues using an intuitive cumulative algorithm. We also introduce a strategy for evaluating the proposed approach, coupled with ~300 annotations of issues in instances from 12 NLG datasets. Our results show that instance-specific issues output by LLM-as-a-qualitative-judge match those annotated by humans in 2/3 cases, and that LLM-as-a-qualitative-judge is capable of producing error type reports resembling the reports composed by human annotators. We also demonstrate in a case study how the use of LLM-as-a-qualitative-judge can substantially improve NLG systems performance. Our code and data are publicly available at https://github.com/tunde-ajayi/llm-as-a-qualitative-judge.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09147
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-as-a-qualitative-judge: automating error analysis in natural language generation
Chirkova, Nadezhda
Ajayi, Tunde Oluwaseyi
Aycock, Seth
Mujahid, Zain Muhammad
Perlić, Vladana
Borisova, Ekaterina
Vartampetian, Markarit
Computation and Language
Artificial Intelligence
Prompting large language models (LLMs) to evaluate generated text, known as LLM-as-a-judge, has become a standard evaluation approach in natural language generation (NLG), but is primarily used as a quantitative tool, i.e. with numerical scores as main outputs. In this work, we propose LLM-as-a-qualitative-judge, an LLM-based evaluation approach with the main output being a structured report of common issue types in the NLG system outputs. Our approach is targeted at providing developers with meaningful insights on what improvements can be done to a given NLG system and consists of two main steps, namely open-ended per-instance issue analysis and clustering of the discovered issues using an intuitive cumulative algorithm. We also introduce a strategy for evaluating the proposed approach, coupled with ~300 annotations of issues in instances from 12 NLG datasets. Our results show that instance-specific issues output by LLM-as-a-qualitative-judge match those annotated by humans in 2/3 cases, and that LLM-as-a-qualitative-judge is capable of producing error type reports resembling the reports composed by human annotators. We also demonstrate in a case study how the use of LLM-as-a-qualitative-judge can substantially improve NLG systems performance. Our code and data are publicly available at https://github.com/tunde-ajayi/llm-as-a-qualitative-judge.
title LLM-as-a-qualitative-judge: automating error analysis in natural language generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.09147