Confidence and Stability of Global and Pairwise Scores in NLP Evaluation

• URL: http://arxiv.org/abs/2507.01633v1
• Date: Wed, 02 Jul 2025 12:05:22 GMT
• Title: Confidence and Stability of Global and Pairwise Scores in NLP Evaluation
• Authors: Georgii Levtsov, Dmitry Ustalov,
• Abstract summary: This paper empirically investigates the strengths and weaknesses of both global scores and pairwise comparisons.<n>We found that while global scores provide more reliable overall rankings, they can underestimate strong models with rare, significant errors or low confidence.
• Score: 7.094351095888013
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the advent of highly capable instruction-tuned neural language models, benchmarking in natural language processing (NLP) is increasingly shifting towards pairwise comparison leaderboards, such as LMSYS Arena, from traditional global pointwise scores (e.g., GLUE, BIG-bench, SWE-bench). This paper empirically investigates the strengths and weaknesses of both global scores and pairwise comparisons to aid decision-making in selecting appropriate model evaluation strategies. Through computational experiments on synthetic and real-world datasets using standard global metrics and the popular Bradley-Terry model for pairwise comparisons, we found that while global scores provide more reliable overall rankings, they can underestimate strong models with rare, significant errors or low confidence. Conversely, pairwise comparisons are particularly effective for identifying strong contenders among models with lower global scores, especially where quality metrics are hard to define (e.g., text generation), though they require more comparisons to converge if ties are frequent. Our code and data are available at https://github.com/HSPyroblast/srw-ranking under a permissive license.

Related papers

• Beyond the Singular: The Essential Role of Multiple Generations in Effective Benchmark Evaluation and Analysis [10.133537818749291]
  Large language models (LLMs) have demonstrated significant utilities in real-world applications.<n> Benchmark evaluations are crucial for assessing the capabilities of LLMs.
  arXiv  Detail & Related papers  (2025-02-13T03:43:33Z)
• A Statistical Framework for Ranking LLM-Based Chatbots [57.59268154690763]
  We propose a statistical framework that incorporates key advancements to address specific challenges in pairwise comparison analysis.<n>First, we introduce a factored tie model that enhances the ability to handle groupings of human-judged comparisons.<n>Second, we extend the framework to model covariance tiers between competitors, enabling deeper insights into performance relationships.<n>Third, we resolve optimization challenges arising from parameter non-uniqueness by introducing novel constraints.
  arXiv  Detail & Related papers  (2024-12-24T12:54:19Z)
• BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices [28.70453947993952]
  We develop an assessment framework considering 46 best practices across an AI benchmark's lifecycle and evaluate 24 AI benchmarks against it. We find that there exist large quality differences and that commonly used benchmarks suffer from significant issues.
  arXiv  Detail & Related papers  (2024-11-20T02:38:24Z)
• Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation [49.3814117521631]
  Standard benchmarks of bias and fairness in large language models (LLMs) measure the association between the user attributes stated or implied by a prompt.<n>We develop analogous RUTEd evaluations from three contexts of real-world use: children's bedtime stories, user personas, and English language learning exercises.<n>We find that standard bias metrics have no significant correlation with the more realistic bias metrics.
  arXiv  Detail & Related papers  (2024-02-20T01:49:15Z)
• 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)
• 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)
• Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction [49.15931834209624]
  We present the first benchmark that simulates the evaluation of open information extraction models in the real world.<n>We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique.<n>By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques.
  arXiv  Detail & Related papers  (2023-05-23T12:05:09Z)
• GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models [60.48306899271866]
  We present a new framework, called GREAT Score, for global robustness evaluation of adversarial perturbation using generative models. We show high correlation and significantly reduced cost of GREAT Score when compared to the attack-based model ranking on RobustBench. GREAT Score can be used for remote auditing of privacy-sensitive black-box models.
  arXiv  Detail & Related papers  (2023-04-19T14:58:27Z)
• How not to Lie with a Benchmark: Rearranging NLP Leaderboards [0.0]
  We examine popular NLP benchmarks' overall scoring methods and rearrange the models by geometric and harmonic mean. We analyze several popular benchmarks including GLUE, SuperGLUE, XGLUE, and XTREME.
  arXiv  Detail & Related papers  (2021-12-02T15:40:52Z)

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.