Order in the Evaluation Court: A Critical Analysis of NLG Evaluation Trends

• URL: http://arxiv.org/abs/2601.07648v1
• Date: Mon, 12 Jan 2026 15:27:58 GMT
• Title: Order in the Evaluation Court: A Critical Analysis of NLG Evaluation Trends
• Authors: Jing Yang, Nils Feldhus, Salar Mohtaj, Leonhard Hennig, Qianli Wang, Eleni Metheniti, Sherzod Hakimov, Charlott Jakob, Veronika Solopova, Konrad Rieck, David Schlangen, Sebastian Möller, Vera Schmitt,
• Abstract summary: We employ an automatic information extraction scheme to gather key information from Natural Language Generation papers.<n>With extracted metadata from 14,171 papers across four major conferences, we reveal several critical findings.<n>We derive practical recommendations to improve the rigor of future NLG evaluation.
• Score: 28.57713768151471
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite advances in Natural Language Generation (NLG), evaluation remains challenging. Although various new metrics and LLM-as-a-judge (LaaJ) methods are proposed, human judgment persists as the gold standard. To systematically review how NLG evaluation has evolved, we employ an automatic information extraction scheme to gather key information from NLG papers, focusing on different evaluation methods (metrics, LaaJ and human evaluation). With extracted metadata from 14,171 papers across four major conferences (ACL, EMNLP, NAACL, and INLG) over the past six years, we reveal several critical findings: (1) Task Divergence: While Dialogue Generation demonstrates a rapid shift toward LaaJ (>40% in 2025), Machine Translation remains locked into n-gram metrics, and Question Answering exhibits a substantial decline in the proportion of studies conducting human evaluation. (2) Metric Inertia: Despite the development of semantic metrics, general-purpose metrics (e.g., BLEU, ROUGE) continue to be widely used across tasks without empirical justification, often lacking the discriminative power to distinguish between specific quality criteria. (3) Human-LaaJ Divergence: Our association analysis challenges the assumption that LLMs act as mere proxies for humans; LaaJ and human evaluations prioritize very different signals, and explicit validation is scarce (<8% of papers comparing the two), with only moderate to low correlation. Based on these observations, we derive practical recommendations to improve the rigor of future NLG evaluation.

Related papers

• The illusion of a perfect metric: Why evaluating AI's words is harder than it looks [0.0]
  Natural Language Generation (NLG) is crucial for the practical adoption of AI.<n>Human evaluation is considered the de-facto standard, but it is expensive and lacks scalability.<n>No single metric has emerged as a definitive solution, resulting in studies using different ones without fully considering the implications.
  arXiv  Detail & Related papers  (2025-08-19T13:22:41Z)
• A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability [36.83105355430611]
  We propose a dual-perspective NLG meta-evaluation framework that focuses on different evaluation capabilities.<n>We also introduce a method of automatically constructing the corresponding benchmarks without requiring new human annotations.
  arXiv  Detail & Related papers  (2025-02-17T17:22:49Z)
• Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability [39.12792986841385]
  In this paper, we construct a large-scale NLG evaluation corpus NLG-Eval with annotations from both human and GPT-4. We also propose an LLM dedicated to NLG evaluation, which has been trained with our designed multi-perspective consistency verification and rating-oriented preference alignment methods. Themis exhibits superior evaluation performance on various NLG tasks, simultaneously generalizing well to unseen tasks and surpassing other evaluation models, including GPT-4.
  arXiv  Detail & Related papers  (2024-06-26T14:04:29Z)
• Is Reference Necessary in the Evaluation of NLG Systems? When and Where? [58.52957222172377]
  We show that reference-free metrics exhibit a higher correlation with human judgment and greater sensitivity to deficiencies in language quality. Our study can provide insight into the appropriate application of automatic metrics and the impact of metric choice on evaluation performance.
  arXiv  Detail & Related papers  (2024-03-21T10:31:11Z)
• Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks [65.69651759036535]
  We analyze whether large language models (LLMs) can serve as reliable alternatives to humans.<n>This paper explores both conventional tasks (e.g., story generation) and alignment tasks (e.g., math reasoning)<n>We find that LLM evaluators can generate unnecessary criteria or omit crucial criteria, resulting in a slight deviation from the experts.
  arXiv  Detail & Related papers  (2023-10-30T17:04:35Z)
• 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)
• Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation [136.16507050034755]
  Existing human evaluation studies for summarization either exhibit a low inter-annotator agreement or have insufficient scale. We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which is based on fine-grained semantic units. We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of 22,000 summary-level annotations over 28 top-performing systems.
  arXiv  Detail & Related papers  (2022-12-15T17:26:05Z)
• Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications [85.24952708195582]
  This study examines the goals, community practices, assumptions, and constraints that shape NLG evaluations. We examine their implications and how they embody ethical considerations.
  arXiv  Detail & Related papers  (2022-05-13T18:00:11Z)
• Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text [23.119724118572538]
  Evaluation practices in natural language generation (NLG) have many known flaws, but improved evaluation approaches are rarely widely adopted. This paper surveys the issues with human and automatic model evaluations and with commonly used datasets in NLG.
  arXiv  Detail & Related papers  (2022-02-14T18:51:07Z)
• Towards Quantifiable Dialogue Coherence Evaluation [126.55560816209756]
  Quantifiable Dialogue Coherence Evaluation (QuantiDCE) is a novel framework aiming to train a quantifiable dialogue coherence metric. QuantiDCE includes two training stages, Multi-Level Ranking (MLR) pre-training and Knowledge Distillation (KD) fine-tuning. Experimental results show that the model trained by QuantiDCE presents stronger correlations with human judgements than the other state-of-the-art metrics.
  arXiv  Detail & Related papers  (2021-06-01T14:11:17Z)

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.