The alignment of large language models (LLMs) with human values is critical for their safe deployment, yet jailbreak attacks can subvert this alignment to elicit harmful outputs from LLMs. In recent years, a proliferation of jailbreak attacks has emerged, accompanied by diverse metrics and judges to assess the harmfulness of the LLM outputs. However, the absence of a systematic benchmark to assess the quality and effectiveness of these metrics and judges undermines the credibility of the reported jailbreak effectiveness and other risks. To address this gap, we introduce HarmMetric Eval, a comprehensive benchmark designed to support both overall and fine-grained evaluation of harmfulness metrics and judges. Our benchmark includes a high-quality dataset of representative harmful prompts paired with diverse harmful and non-harmful model responses, alongside a flexible scoring mechanism compatible with various metrics and judges. With HarmMetric Eval, our extensive experiments uncover a surprising result: two conventional metrics--METEOR and ROUGE-1--outperform LLM-based judges in evaluating the harmfulness of model responses, challenging prevailing beliefs about LLMs' superiority in this domain. Our dataset is publicly available at https://huggingface.co/datasets/qusgo/HarmMetric_Eval, and the code is available at https://anonymous.4open.science/r/HarmMetric-Eval-4CBE.

EXplainable machine learning (XML) has recently emerged to address the mystery mechanisms of machine learning (ML) systems by interpreting their 'black box' results. Despite the development of various explanation methods, determining the most suitable XML method for specific ML contexts remains unclear, highlighting the need for effective evaluation of explanations. The evaluating capabilities of the Transformer-based large language model (LLM) present an opportunity to adopt LLM-as-a-Judge for assessing explanations. In this paper, we propose a workflow that integrates both LLM-based and human judges for evaluating explanations. We examine how LLM-based judges evaluate the quality of various explanation methods and compare their evaluation capabilities to those of human judges within an iris classification scenario, employing both subjective and objective metrics. We conclude that while LLM-based judges effectively assess the quality of explanations using subjective metrics, they are not yet sufficiently developed to replace human judges in this role.

LLM-based judges have emerged as a scalable alternative to human evaluation and are increasingly used to assess, compare, and improve models. However, the reliability of LLM-based judges themselves is rarely scrutinized. As LLMs become more advanced, their responses grow more sophisticated, requiring stronger judges to evaluate them. Existing benchmarks primarily focus on a judge's alignment with human preferences, but often fail to account for more challenging tasks where crowdsourced human preference is a poor indicator of factual and logical correctness. To address this, we propose a novel evaluation framework to objectively evaluate LLM-based judges. Based on this framework, we propose JudgeBench, a benchmark for evaluating LLM-based judges on challenging response pairs spanning knowledge, reasoning, math, and coding. Our comprehensive evaluation on a collection of prompted judges, fine-tuned judges, multi-agent judges, and reward models shows that JudgeBench poses a significantly greater challenge than previous benchmarks, with many strong models (e.g., GPT-4o) performing just slightly better than random guessing. Overall, JudgeBench offers a reliable platform for assessing increasingly advanced LLM-based judges. Data and code are available at https://github.com/ Large Language Models (LLMs) have demonstrated remarkable success in recent years and are still evolving at a rapid pace. With more advanced AI models coming out every month, a central challenge is how to evaluate, compare, and supervise these models. While human judgments have traditionally been the gold standard in evaluating and supervising language models, collecting human judgments is often costly and time-consuming. As an alternative, using LLM-based judges (Zheng et al., 2024) has become a scalable paradigm in addressing this limitation, and has been increasingly adopted to evaluate and rank models. Moreover, these LLM-based judges are now integral to enhancing models' capability, serving as reward models during training (Yuan et al., 2024; Luo et al., 2024a), and acting as verifiers during inference to select the best response from multiple candidates (Cobbe et al., 2021; Lightman et al., 2023). Despite the widespread adoption, a fundamental question remains: How reliable are these LLMbased judges themselves? Since LLMs themselves are prone to make logical and factual mistakes, how can we trust that LLM-based judges are accurate and objective? To evaluate LLM-based judges, many prior works have focused on these judges' agreement with human preference (Dubois et al., 2024; Zheng et al., 2024; Zhang et al., 2023; Wang et al., 2023a). The core assumption implied in these works is that crowdsourced human annotators will evaluate the responses objectively and not make mistakes. Prompt: Rewrite the sentence using gender-neutral language: A salesman is giving a presentation. A salesperson is giving a presentation.

Rating-based human evaluation has become an essential tool to accurately evaluate the impressive performance of Large language models (LLMs). However, current rating systems suffer from several critical limitations. Specifically, they fail to account for human biases that significantly influence evaluation results, require large and expensive preference datasets to obtain accurate ratings, and do not facilitate meaningful comparisons of model ratings across different tasks. To address these issues, we introduce Polyrating, an expressive and flexible rating system based on maximum a posteriori estimation that enables a more nuanced and thorough analysis of model performance at lower costs. Polyrating can detect and quantify biases affecting human preferences, ensuring fairer model comparisons. Furthermore, Polyrating can reduce the cost of human evaluations by up to $41\%$ for new models and up to $77\%$ for new tasks by leveraging existing benchmark scores. Lastly, Polyrating enables direct comparisons of ratings across different tasks, providing a comprehensive understanding of an LLMs' strengths, weaknesses, and relative performance across different applications.