Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge

• URL: http://arxiv.org/abs/2410.03775v1
• Date: Thu, 3 Oct 2024 03:08:29 GMT
• Title: Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge
• Authors: Aparna Elangovan, Jongwoo Ko, Lei Xu, Mahsa Elyasi, Ling Liu, Sravan Bodapati, Dan Roth,
• Abstract summary: We show how *relying on a single aggregate correlation score* can obscure fundamental differences between human behavior and automatic evaluation methods. We propose stratifying results by human label uncertainty to provide a more robust analysis of automatic evaluation performance.
• Score: 51.93909886542317
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The effectiveness of automatic evaluation of generative models is typically measured by comparing it to human evaluation using correlation metrics. However, metrics like Krippendorff's $\alpha$ and Randolph's $\kappa$, originally designed to measure the reliability of human labeling, make assumptions about human behavior and the labeling process. In this paper, we show how *relying on a single aggregate correlation score* can obscure fundamental differences between human behavior and automatic evaluation methods, including LLM-as-a-Judge. Specifically, we demonstrate that when the proportion of samples with variation or uncertainty in human labels (gathered during human evaluation) is relatively high, machine labels (generated by automatic evaluation methods) may superficially appear to have similar or better correlation with the human majority label compared to human-to-human (HH) correlation. This can create the misleading impression that automatic evaluation is accurate enough to approximate the human majority label. However, as the proportion of samples with consistent human labels increases, the correlation between machine labels and human majority labels declines, falling below HH correlation. Based on these findings, we first propose stratifying results by human label uncertainty to provide a more robust analysis of automatic evaluation performance. Second, recognizing that uncertainty and variation are inherent in perception-based human evaluations, such as those involving attitudes or preferences, we introduce a new metric - *binned Jensen-Shannon Divergence for perception* for such scenarios to better measure the effectiveness of automatic evaluations. Third, we present visualization techniques -- *perception charts*, to compare the strengths and limitations of automatic evaluation and to contextualize correlation measures appropriately

Related papers

• Aligning Model Evaluations with Human Preferences: Mitigating Token Count Bias in Language Model Assessments [2.1370543868467275]
  This follow-up paper explores methods to align Large Language Models evaluator preferences with human evaluations. We employed Bayesian statistics and a t-test to quantify this bias and developed a recalibration procedure to adjust the GPTScorer. Our findings significantly improve aligning the recalibrated LLM evaluator with human evaluations across multiple use cases.
  arXiv  Detail & Related papers  (2024-07-05T09:26:40Z)
• It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density Estimation [15.8765167340819]
  Human annotator simulation (HAS) serves as a cost-effective substitute for human evaluation such as data annotation and system assessment. Human perception and behaviour during human evaluation exhibit inherent variability due to diverse cognitive processes and subjective interpretations. This paper introduces a novel meta-learning framework that treats HAS as a zero-shot density estimation problem.
  arXiv  Detail & Related papers  (2023-09-30T20:54:59Z)
• What is the Best Automated Metric for Text to Motion Generation? [19.71712698183703]
  There is growing interest in generating skeleton-based human motions from natural language descriptions. Human evaluation is the ultimate accuracy measure for this task, and automated metrics should correlate well with human quality judgments. This paper systematically studies which metrics best align with human evaluations and proposes new metrics that align even better.
  arXiv  Detail & Related papers  (2023-09-19T01:59:54Z)
• Gender Biases in Automatic Evaluation Metrics for Image Captioning [87.15170977240643]
  We conduct a systematic study of gender biases in model-based evaluation metrics for image captioning tasks. We demonstrate the negative consequences of using these biased metrics, including the inability to differentiate between biased and unbiased generations. We present a simple and effective way to mitigate the metric bias without hurting the correlations with human judgments.
  arXiv  Detail & Related papers  (2023-05-24T04:27:40Z)
• Social Biases in Automatic Evaluation Metrics for NLG [53.76118154594404]
  We propose an evaluation method based on Word Embeddings Association Test (WEAT) and Sentence Embeddings Association Test (SEAT) to quantify social biases in evaluation metrics. We construct gender-swapped meta-evaluation datasets to explore the potential impact of gender bias in image caption and text summarization tasks.
  arXiv  Detail & Related papers  (2022-10-17T08:55:26Z)
• Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metrics [64.81682222169113]
  How reliably an automatic summarization evaluation metric replicates human judgments of summary quality is quantified by system-level correlations. We identify two ways in which the definition of the system-level correlation is inconsistent with how metrics are used to evaluate systems in practice.
  arXiv  Detail & Related papers  (2022-04-21T15:52:14Z)
• Dynamic Human Evaluation for Relative Model Comparisons [8.843915018287476]
  We present a dynamic approach to measure the required number of human annotations when evaluating generated outputs in relative comparison settings. We propose an agent-based framework of human evaluation to assess multiple labelling strategies and methods to decide the better model in a simulation and a crowdsourcing case study.
  arXiv  Detail & Related papers  (2021-12-15T11:32:13Z)
• 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)
• Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach [84.02388020258141]
  We propose a new framework named ENIGMA for estimating human evaluation scores based on off-policy evaluation in reinforcement learning. ENIGMA only requires a handful of pre-collected experience data, and therefore does not involve human interaction with the target policy during the evaluation. Our experiments show that ENIGMA significantly outperforms existing methods in terms of correlation with human evaluation scores.
  arXiv  Detail & Related papers  (2021-02-20T03:29:20Z)

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.