LLM-as-a-qualitative-judge: automating error analysis in natural language generation

• URL: http://arxiv.org/abs/2506.09147v2
• Date: Tue, 29 Jul 2025 21:11:25 GMT
• Title: LLM-as-a-qualitative-judge: automating error analysis in natural language generation
• Authors: Nadezhda Chirkova, Tunde Oluwaseyi Ajayi, Seth Aycock, Zain Muhammad Mujahid, Vladana Perlić, Ekaterina Borisova, Markarit Vartampetian,
• Abstract summary: We propose an evaluation approach based on large language models (LLMs) for natural language generation (NLG)<n>Our approach consists of open-ended per-instance issue analysis and clustering of the discovered issues using an intuitive cumulative algorithm.<n>Our results show that LLM-as-a-qualitative-judge correctly recognizes instance-specific issues in 2/3 cases and is capable of producing error type reports resembling the reports composed by human annotators.
• Score: 6.705171415653766
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 LLM-as-a-qualitative-judge correctly recognizes instance-specific issues in 2/3 cases and is capable of producing error type reports resembling the reports composed by human annotators. Our code and data are publicly available at https://github.com/tunde-ajayi/llm-as-a-qualitative-judge.

Related papers

• On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization [54.965787768076254]
  Large Language Models have been recently exploited as judges for complex natural language processing tasks, such as Q&A.<n>We study the effectiveness of LLMs-as-a-judge for two code-related tasks, namely code generation and code summarization.
  arXiv  Detail & Related papers  (2025-07-22T13:40:26Z)
• Potential and Perils of Large Language Models as Judges of Unstructured Textual Data [0.631976908971572]
  This research investigates the effectiveness of LLM-as-judge models to evaluate the thematic alignment of summaries generated by other LLMs.<n>Our findings reveal that while LLM-as-judge offer a scalable solution comparable to human raters, humans may still excel at detecting subtle, context-specific nuances.
  arXiv  Detail & Related papers  (2025-01-14T14:49:14Z)
• When LLMs Struggle: Reference-less Translation Evaluation for Low-resource Languages [9.138590152838754]
  Segment-level quality estimation (QE) is a challenging cross-lingual language understanding task.<n>We comprehensively evaluate large language models (LLMs) in zero/few-shot scenarios.<n>Our results indicate that prompt-based approaches are outperformed by the encoder-based fine-tuned QE models.
  arXiv  Detail & Related papers  (2025-01-08T12:54:05Z)
• Leveraging LLMs for Dialogue Quality Measurement [27.046917937460798]
  Large language models (LLMs) show robust zeroshot and few-shot capabilities across NLP tasks. Manipulating factors such as model size, in-context examples, and selection techniques, we examine "chain-of-thought" (CoT) reasoning and label extraction procedures. Our results indicate that LLMs that are suitably fine-tuned and have sufficient reasoning capabilities can be leveraged for automated dialogue evaluation.
  arXiv  Detail & Related papers  (2024-06-25T06:19:47Z)
• DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
  We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity. Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data. Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
  arXiv  Detail & Related papers  (2024-06-25T04:27:53Z)
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal [64.9938658716425]
  SORRY-Bench is a proposed benchmark for evaluating large language models' (LLMs) ability to recognize and reject unsafe user requests.<n>First, existing methods often use coarse-grained taxonomy of unsafe topics, and are over-representing some fine-grained topics.<n>Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations.
  arXiv  Detail & Related papers  (2024-06-20T17:56:07Z)
• Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
  We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
  arXiv  Detail & Related papers  (2024-04-04T15:36:53Z)
• Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs [30.179703001666173]
  Factuality issue is a critical concern for Large Language Models (LLMs) We propose GraphEval to evaluate an LLM's performance using a substantially large test dataset. Test dataset is retrieved from a large knowledge graph with more than 10 million facts without expensive human efforts.
  arXiv  Detail & Related papers  (2024-04-01T06:01:17Z)
• Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization [132.25202059478065]
  We benchmark large language models (LLMs) on instruction controllable text summarization. Our study reveals that instruction controllable text summarization remains a challenging task for LLMs.
  arXiv  Detail & Related papers  (2023-11-15T18:25:26Z)
• Which is better? Exploring Prompting Strategy For LLM-based Metrics [6.681126871165601]
  This paper describes the DSBA submissions to the Prompting Large Language Models as Explainable Metrics shared task. Traditional similarity-based metrics such as BLEU and ROUGE have shown to misalign with human evaluation and are ill-suited for open-ended generation tasks.
  arXiv  Detail & Related papers  (2023-11-07T06:36:39Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models [55.60306377044225]
  Large language models (LLMs) have enabled impressive zero-shot capabilities across various natural language tasks. This paper explores two options for exploiting the emergent abilities of LLMs for zero-shot NLG assessment. For moderate-sized open-source LLMs, such as FlanT5 and Llama2-chat, comparative assessment is superior to prompt scoring.
  arXiv  Detail & Related papers  (2023-07-15T22:02:12Z)
• G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment [64.01972723692587]
  We present G-Eval, a framework of using large language models with chain-of-thoughts (CoT) and a form-filling paradigm to assess the quality of NLG outputs. We show that G-Eval with GPT-4 as the backbone model achieves a Spearman correlation of 0.514 with human on summarization task, outperforming all previous methods by a large margin.
  arXiv  Detail & Related papers  (2023-03-29T12:46:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.