References Matter: Investigating the Impact of Reference Set Variation on Summarization Evaluation

• URL: http://arxiv.org/abs/2506.14335v2
• Date: Fri, 25 Jul 2025 14:40:41 GMT
• Title: References Matter: Investigating the Impact of Reference Set Variation on Summarization Evaluation
• Authors: Silvia Casola, Yang Janet Liu, Siyao Peng, Oliver Kraus, Albert Gatt, Barbara Plank,
• Abstract summary: This work examines the sensitivity of widely used reference-based metrics in relation to the choice of reference sets.<n>We demonstrate that many popular metrics exhibit significant instability.<n>This instability is particularly concerning for n-gram-based metrics like ROUGE, where model rankings vary depending on the reference sets.
• Score: 25.428322811598722
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Human language production exhibits remarkable richness and variation, reflecting diverse communication styles and intents. However, this variation is often overlooked in summarization evaluation. While having multiple reference summaries is known to improve correlation with human judgments, the impact of the reference set on reference-based metrics has not been systematically investigated. This work examines the sensitivity of widely used reference-based metrics in relation to the choice of reference sets, analyzing three diverse multi-reference summarization datasets: SummEval, GUMSum, and DUC2004. We demonstrate that many popular metrics exhibit significant instability. This instability is particularly concerning for n-gram-based metrics like ROUGE, where model rankings vary depending on the reference sets, undermining the reliability of model comparisons. We also collect human judgments on LLM outputs for genre-diverse data and examine their correlation with metrics to supplement existing findings beyond newswire summaries, finding weak-to-no correlation. Taken together, we recommend incorporating reference set variation into summarization evaluation to enhance consistency alongside correlation with human judgments, especially when evaluating LLMs.

Related papers

• Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation [39.5140467914755]
  This paper analyzes 12 common correlation measures using a large amount of real-world data from six widely-used NLG evaluation datasets and 32 evaluation metrics.<n>We find that the measure using global grouping and Pearson correlation coefficient exhibits the best performance in both discriminative power and ranking consistency.
  arXiv  Detail & Related papers  (2024-10-22T09:14:21Z)
• Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics [4.881135687863645]
  We introduce a reference-free metric that correlates well with human evaluated relevance, while being very cheap to compute. We show that this metric can also be used alongside reference-based metrics to improve their robustness in low quality reference settings.
  arXiv  Detail & Related papers  (2024-10-08T11:09:25Z)
• VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models [57.43276586087863]
  Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the models generate plausible-sounding but factually incorrect outputs. Existing benchmarks are often limited in scope, focusing mainly on object hallucinations. We introduce a multi-dimensional benchmark covering objects, attributes, and relations, with challenging images selected based on associative biases.
  arXiv  Detail & Related papers  (2024-04-22T04:49:22Z)
• Learning Evaluation Models from Large Language Models for Sequence Generation [61.8421748792555]
  We propose a three-stage evaluation model training method that utilizes large language models to generate labeled data for model-based metric development.<n> Experimental results on the SummEval benchmark demonstrate that CSEM can effectively train an evaluation model without human-labeled data.
  arXiv  Detail & Related papers  (2023-08-08T16:41:16Z)
• Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation [55.92852268168816]
  N-gram matching-based evaluation metrics, such as BLEU and chrF, are widely utilized across a range of natural language generation (NLG) tasks. Recent studies have revealed a weak correlation between these matching-based metrics and human evaluations. We propose to utilize textitmultiple references to enhance the consistency between these metrics and human evaluations.
  arXiv  Detail & Related papers  (2023-08-06T14:49:26Z)
• Redundancy Aware Multi-Reference Based Gainwise Evaluation of Extractive Summarization [3.5297361401370044]
  The ROUGE metric has been criticized for its lack of semantic awareness and its ignorance about the ranking quality of the extractive summarizer. Previous research has introduced a gain-based automated metric called Sem-nCG that addresses these issues. We propose a redundancy-aware Sem-nCG metric and demonstrate how it can be used to evaluate model summaries against multiple references.
  arXiv  Detail & Related papers  (2023-08-04T11:47:19Z)
• Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References [123.39034752499076]
  Div-Ref is a method to enhance evaluation benchmarks by enriching the number of references. We conduct experiments to empirically demonstrate that diversifying the expression of reference can significantly enhance the correlation between automatic evaluation and human evaluation.
  arXiv  Detail & Related papers  (2023-05-24T11:53:29Z)
• DocAsRef: An Empirical Study on Repurposing Reference-Based Summary Quality Metrics Reference-Freely [29.4981129248937]
  We propose that some reference-based metrics can be effectively adapted to assess a system summary against its corresponding reference. After being repurposed reference-freely, the zero-shot BERTScore consistently outperforms its original reference-based version. It also excels in comparison to most existing reference-free metrics and closely competes with zero-shot summary evaluators based on GPT-3.5.
  arXiv  Detail & Related papers  (2022-12-20T06:01:13Z)
• REAM$\sharp$: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation [63.46331073232526]
  We present an enhancement approach to Reference-based EvAluation Metrics for open-domain dialogue systems. A prediction model is designed to estimate the reliability of the given reference set. We show how its predicted results can be helpful to augment the reference set, and thus improve the reliability of the metric.
  arXiv  Detail & Related papers  (2021-05-30T10:04:13Z)
• A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methods [60.04142561088524]
  We find that the confidence intervals are rather wide, demonstrating high uncertainty in how reliable automatic metrics truly are. Although many metrics fail to show statistical improvements over ROUGE, two recent works, QAEval and BERTScore, do in some evaluation settings.
  arXiv  Detail & Related papers  (2021-03-31T18:28:14Z)

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.