Large Language Models are Inconsistent and Biased Evaluators
- URL: http://arxiv.org/abs/2405.01724v1
- Date: Thu, 2 May 2024 20:42:28 GMT
- Title: Large Language Models are Inconsistent and Biased Evaluators
- Authors: Rickard Stureborg, Dimitris Alikaniotis, Yoshi Suhara,
- Abstract summary: We show that Large Language Models (LLMs) are biased evaluators as they exhibit familiarity bias and show skewed distributions of ratings.
We also found that LLMs are inconsistent evaluators, showing low "inter-sample" agreement and sensitivity to prompt differences that are insignificant to human understanding of text quality.
- Score: 2.136983452580014
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The zero-shot capability of Large Language Models (LLMs) has enabled highly flexible, reference-free metrics for various tasks, making LLM evaluators common tools in NLP. However, the robustness of these LLM evaluators remains relatively understudied; existing work mainly pursued optimal performance in terms of correlating LLM scores with human expert scores. In this paper, we conduct a series of analyses using the SummEval dataset and confirm that LLMs are biased evaluators as they: (1) exhibit familiarity bias-a preference for text with lower perplexity, (2) show skewed and biased distributions of ratings, and (3) experience anchoring effects for multi-attribute judgments. We also found that LLMs are inconsistent evaluators, showing low "inter-sample" agreement and sensitivity to prompt differences that are insignificant to human understanding of text quality. Furthermore, we share recipes for configuring LLM evaluators to mitigate these limitations. Experimental results on the RoSE dataset demonstrate improvements over the state-of-the-art LLM evaluators.
Related papers
- Towards Understanding the Robustness of LLM-based Evaluations under Perturbations [9.944512689015998]
Large Language Models (LLMs) can serve as automatic evaluators for non-standardized metrics in summarization and dialog-based tasks.
We conduct experiments across multiple prompting strategies to examine how LLMs fare as quality evaluators when compared with human judgments.
arXiv Detail & Related papers (2024-12-12T13:31:58Z) - Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge [84.34545223897578]
Despite their excellence in many domains, potential issues are under-explored, undermining their reliability and the scope of their utility.
We identify 12 key potential biases and propose a new automated bias quantification framework-CALM- which quantifies and analyzes each type of bias in LLM-as-a-Judge.
Our work highlights the need for stakeholders to address these issues and remind users to exercise caution in LLM-as-a-Judge applications.
arXiv Detail & Related papers (2024-10-03T17:53:30Z) - Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates [10.091146498861333]
Commercial large language models (LLMs) like GPT-4 have been recently employed to evaluate and compare different alignment approaches.
We develop a framework to evaluate, compare, and visualize the reliability and alignment of LLM judges.
arXiv Detail & Related papers (2024-08-23T11:49:01Z) - DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation [75.81096662788254]
Large Language Models (LLMs) are scalable and economical evaluators.
The question of how reliable these evaluators are has emerged as a crucial research question.
We propose Decompose and Aggregate, which breaks down the evaluation process into different stages based on pedagogical practices.
arXiv Detail & Related papers (2024-05-24T08:12:30Z) - RepEval: Effective Text Evaluation with LLM Representation [55.26340302485898]
RepEval is a metric that leverages the projection of Large Language Models (LLMs) representations for evaluation.
Our work underscores the richness of information regarding text quality embedded within LLM representations, offering insights for the development of new metrics.
arXiv Detail & Related papers (2024-04-30T13:50:55Z) - Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators [48.54465599914978]
Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language.
LLMs still exhibit biases in evaluation and often struggle to generate coherent evaluations that align with human assessments.
We introduce Pairwise-preference Search (PAIRS), an uncertainty-guided search-based rank aggregation method that employs LLMs to conduct pairwise comparisons locally and efficiently ranks candidate texts globally.
arXiv Detail & Related papers (2024-03-25T17:11:28Z) - PRE: A Peer Review Based Large Language Model Evaluator [14.585292530642603]
Existing paradigms rely on either human annotators or model-based evaluators to evaluate the performance of LLMs.
We propose a novel framework that can automatically evaluate LLMs through a peer-review process.
arXiv Detail & Related papers (2024-01-28T12:33:14Z) - Evaluating Large Language Models at Evaluating Instruction Following [54.49567482594617]
We introduce a challenging meta-evaluation benchmark, LLMBar, designed to test the ability of an LLM evaluator in discerning instruction-following outputs.
We discover that different evaluators exhibit distinct performance on LLMBar and even the highest-scoring ones have substantial room for improvement.
arXiv Detail & Related papers (2023-10-11T16:38:11Z) - On Learning to Summarize with Large Language Models as References [101.79795027550959]
Large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets.
We study an LLM-as-reference learning setting for smaller text summarization models to investigate whether their performance can be substantially improved.
arXiv Detail & Related papers (2023-05-23T16:56:04Z)
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.