LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods

The rapid advancement of Large Language Models (LLMs) has driven their expanding application across various fields. One of the most promising applications is their role as evaluators based on natural language responses, referred to as ''LLMs-as-judges''. This framework has attracted growing attention from both academia and industry due to their excellent effectiveness, ability to generalize across tasks, and interpretability in the form of natural language. This paper presents a comprehensive survey of the LLMs-as-judges paradigm from five key perspectives: Functionality, Methodology, Applications, Meta-evaluation, and Limitations. We begin by providing a systematic definition of LLMs-as-Judges and introduce their functionality (Why use LLM judges?). Then we address methodology to construct an evaluation system with LLMs (How to use LLM judges?). Additionally, we investigate the potential domains for their application (Where to use LLM judges?) and discuss methods for evaluating them in various contexts (How to evaluate LLM judges?). Finally, we provide a detailed analysis of the limitations of LLM judges and discuss potential future directions. Through a structured and comprehensive analysis, we aim aims to provide insights on the development and application of LLMs-as-judges in both research and practice. We will continue to maintain the relevant resource list at https://github.com/CSHaitao/Awesome-LLMs-as-Judges.

De-biased Multimodal Electrocardiogram Analysis

Multimodal large language models (MLLMs) are increasingly being applied in the medical field, particularly in medical imaging. However, developing MLLMs for ECG signals, which are crucial in clinical settings, has been a significant challenge beyond medical imaging. Previous studies have attempted to address this by converting ECGs into several text tags using an external classifier in a training-free manner. However, this approach significantly compresses the information in ECGs and underutilizes the reasoning capabilities of LLMs. In this work, we directly feed the embeddings of ECGs into the LLM through a projection layer, retaining more information about ECGs and better leveraging the reasoning abilities of LLMs. Our method can also effectively handle a common situation in clinical practice where it is necessary to compare two ECGs taken at different times. Recent studies found that MLLMs may rely solely on text input to provide answers, ignoring inputs from other modalities. We analyzed this phenomenon from a causal perspective in the context of ECG MLLMs and discovered that the confounder, severity of illness, introduces a spurious correlation between the question and answer, leading the model to rely on this spurious correlation and ignore the ECG input. Such models do not comprehend the ECG input and perform poorly in adversarial tests where different expressions of the same question are used in the training and testing sets. We designed a de-biased pre-training method to eliminate the confounder's effect according to the theory of backdoor adjustment. Our model performed well on the ECG-QA task under adversarial testing and demonstrated zero-shot capabilities. An interesting random ECG test further validated that our model effectively understands and utilizes the input ECG signal.

Large-scale cross-modality pretrained model enhances cardiovascular state estimation and cardiomyopathy detection from electrocardiograms: An AI system development and multi-center validation study

Cardiovascular diseases (CVDs) present significant challenges for early and accurate diagnosis. While cardiac magnetic resonance imaging (CMR) is the gold standard for assessing cardiac function and diagnosing CVDs, its high cost and technical complexity limit accessibility. In contrast, electrocardiography (ECG) offers promise for large-scale early screening. This study introduces CardiacNets, an innovative model that enhances ECG analysis by leveraging the diagnostic strengths of CMR through cross-modal contrastive learning and generative pretraining. CardiacNets serves two primary functions: (1) it evaluates detailed cardiac function indicators and screens for potential CVDs, including coronary artery disease, cardiomyopathy, pericarditis, heart failure and pulmonary hypertension, using ECG input; and (2) it enhances interpretability by generating high-quality CMR images from ECG data. We train and validate the proposed CardiacNets on two large-scale public datasets (the UK Biobank with 41,519 individuals and the MIMIC-IV-ECG comprising 501,172 samples) as well as three private datasets (FAHZU with 410 individuals, SAHZU with 464 individuals, and QPH with 338 individuals), and the findings demonstrate that CardiacNets consistently outperforms traditional ECG-only models, substantially improving screening accuracy. Furthermore, the generated CMR images provide valuable diagnostic support for physicians of all experience levels. This proof-of-concept study highlights how ECG can facilitate cross-modal insights into cardiac function assessment, paving the way for enhanced CVD screening and diagnosis at a population level.

CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges

The use of large language models (LLMs) as automated evaluation tools to assess the quality of generated natural language, known as LLMs-as-Judges, has demonstrated promising capabilities and is rapidly gaining widespread attention. However, when applied to pairwise comparisons of candidate responses, LLM-based evaluators often exhibit selection bias. Specifically, their judgments may become inconsistent when the option positions or ID tokens are swapped, compromising the effectiveness and fairness of the evaluation result. To address this challenge, we introduce CalibraEval, a novel label-free method for mitigating selection bias during inference. Specifically, CalibraEval reformulates debiasing as an optimization task aimed at adjusting observed prediction distributions to align with unbiased prediction distributions. To solve this optimization problem, we propose a non-parametric order-preserving algorithm (NOA). This algorithm leverages the partial order relationships between model prediction distributions, thereby eliminating the need for explicit labels and precise mathematical function modeling.Empirical evaluations of LLMs in multiple representative benchmarks demonstrate that CalibraEval effectively mitigates selection bias and improves performance compared to existing debiasing methods. This work marks a step toward building more robust and unbiased automated evaluation frameworks, paving the way for improved reliability in AI-driven assessments

An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation

With the rapid development of large language models (LLMs), how to efficiently evaluate them has become an important research question. Existing evaluation methods often suffer from high costs, limited test formats, the need of human references, and systematic evaluation biases. To address these limitations, our study introduces the Auto-PRE, an automatic LLM evaluation framework based on peer review. In contrast to previous studies that rely on human annotations, Auto-PRE selects evaluator LLMs automatically based on their inherent traits including consistency, self-confidence, and pertinence. We conduct extensive experiments on three tasks: summary generation, non-factoid question-answering, and dialogue generation. Experimental results indicate our Auto-PRE achieves state-of-the-art performance at a lower cost. Moreover, our study highlights the impact of prompt strategies and evaluation formats on evaluation performance, offering guidance for method optimization in the future.

LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models

Large language models (LLMs) have made significant progress in natural language processing tasks and demonstrate considerable potential in the legal domain. However, legal applications demand high standards of accuracy, reliability, and fairness. Applying existing LLMs to legal systems without careful evaluation of their potential and limitations could pose significant risks in legal practice. To this end, we introduce a standardized comprehensive Chinese legal benchmark LexEval. This benchmark is notable in the following three aspects: (1) Ability Modeling: We propose a new taxonomy of legal cognitive abilities to organize different tasks. (2) Scale: To our knowledge, LexEval is currently the largest Chinese legal evaluation dataset, comprising 23 tasks and 14,150 questions. (3) Data: we utilize formatted existing datasets, exam datasets and newly annotated datasets by legal experts to comprehensively evaluate the various capabilities of LLMs. LexEval not only focuses on the ability of LLMs to apply fundamental legal knowledge but also dedicates efforts to examining the ethical issues involved in their application. We evaluated 38 open-source and commercial LLMs and obtained some interesting findings. The experiments and findings offer valuable insights into the challenges and potential solutions for developing Chinese legal systems and LLM evaluation pipelines. The LexEval dataset and leaderboard are publicly available at \url{https://github.com/CSHaitao/LexEval} and will be continuously updated.

Towards an In-Depth Comprehension of Case Relevance for Better Legal Retrieval

Legal retrieval techniques play an important role in preserving the fairness and equality of the judicial system. As an annually well-known international competition, COLIEE aims to advance the development of state-of-the-art retrieval models for legal texts. This paper elaborates on the methodology employed by the TQM team in COLIEE2024.Specifically, we explored various lexical matching and semantic retrieval models, with a focus on enhancing the understanding of case relevance. Additionally, we endeavor to integrate various features using the learning-to-rank technique. Furthermore, fine heuristic pre-processing and post-processing methods have been proposed to mitigate irrelevant information. Consequently, our methodology achieved remarkable performance in COLIEE2024, securing first place in Task 1 and third place in Task 3. We anticipate that our proposed approach can contribute valuable insights to the advancement of legal retrieval technology.

DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment

Recent research demonstrates the effectiveness of using pre-trained language models for legal case retrieval. Most of the existing works focus on improving the representation ability for the contextualized embedding of the [CLS] token and calculate relevance using textual semantic similarity. However, in the legal domain, textual semantic similarity does not always imply that the cases are relevant enough. Instead, relevance in legal cases primarily depends on the similarity of key facts that impact the final judgment. Without proper treatments, the discriminative ability of learned representations could be limited since legal cases are lengthy and contain numerous non-key facts. To this end, we introduce DELTA, a discriminative model designed for legal case retrieval. The basic idea involves pinpointing key facts in legal cases and pulling the contextualized embedding of the [CLS] token closer to the key facts while pushing away from the non-key facts, which can warm up the case embedding space in an unsupervised manner. To be specific, this study brings the word alignment mechanism to the contextual masked auto-encoder. First, we leverage shallow decoders to create information bottlenecks, aiming to enhance the representation ability. Second, we employ the deep decoder to enable translation between different structures, with the goal of pinpointing key facts to enhance discriminative ability. Comprehensive experiments conducted on publicly available legal benchmarks show that our approach can outperform existing state-of-the-art methods in legal case retrieval. It provides a new perspective on the in-depth understanding and processing of legal case documents.

BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models

Large Language Models (LLMs) like ChatGPT and GPT-4 are versatile and capable of addressing a diverse range of tasks. However, general LLMs, which are developed on open-domain data, may lack the domain-specific knowledge essential for tasks in vertical domains, such as legal, medical, etc. To address this issue, previous approaches either conduct continuous pre-training with domain-specific data or employ retrieval augmentation to support general LLMs. Unfortunately, these strategies are either cost-intensive or unreliable in practical applications. To this end, we present a novel framework named BLADE, which enhances Black-box LArge language models with small Domain-spEcific models. BLADE consists of a black-box LLM and a small domain-specific LM. The small LM preserves domain-specific knowledge and offers specialized insights, while the general LLM contributes robust language comprehension and reasoning capabilities. Specifically, our method involves three steps: 1) pre-training the small LM with domain-specific data, 2) fine-tuning this model using knowledge instruction data, and 3) joint Bayesian optimization of the general LLM and the small LM. Extensive experiments conducted on public legal and medical benchmarks reveal that BLADE significantly outperforms existing approaches. This shows the potential of BLADE as an effective and cost-efficient solution in adapting general LLMs for vertical domains.

Evaluation Ethics of LLMs in Legal Domain

In recent years, the utilization of large language models for natural language dialogue has gained momentum, leading to their widespread adoption across various domains. However, their universal competence in addressing challenges specific to specialized fields such as law remains a subject of scrutiny. The incorporation of legal ethics into the model has been overlooked by researchers. We asserts that rigorous ethic evaluation is essential to ensure the effective integration of large language models in legal domains, emphasizing the need to assess domain-specific proficiency and domain-specific ethic. To address this, we propose a novelty evaluation methodology, utilizing authentic legal cases to evaluate the fundamental language abilities, specialized legal knowledge and legal robustness of large language models (LLMs). The findings from our comprehensive evaluation contribute significantly to the academic discourse surrounding the suitability and performance of large language models in legal domains.