pith. sign in

arxiv: 2408.08808 · v3 · pith:43K6SI5Nnew · submitted 2024-08-16 · 💻 cs.LG · cs.AI

Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge

classification 💻 cs.LG cs.AI
keywords acrossevaluationmodelsbenchmarkagreementarenabettercategories
0
0 comments X
read the original abstract

Large Language Models (LLMs) have revolutionized the landscape of machine learning, yet current benchmarks often fall short in capturing the diverse behavior of these models in real-world applications. A benchmark's usefulness is determined by its ability to clearly differentiate between models of varying capabilities (separability) and closely align with human preferences. Existing frameworks like Alpaca-Eval 2.0 LC \cite{dubois2024lengthcontrolledalpacaevalsimpleway} and Arena-Hard v0.1 \cite{li2024crowdsourced} are limited by their focus on general-purpose queries and lack of diversity across domains such as law, medicine, and multilingual contexts. In this paper, we address these limitations by introducing a novel data pipeline that curates diverse, domain-specific evaluation sets tailored for LLM-as-a-Judge frameworks. Our approach leverages a combination of manual curation, semi-supervised learning to generate clusters, and stratified sampling to ensure balanced representation across a wide range of domains and languages. The resulting evaluation set, which includes 1573 samples across 14 categories, demonstrates high separability (84\%) across ten top-ranked models, and agreement (84\%) with Chatbot Arena and (0.915) Spearman correlation. The agreement values are 9\% better than Arena Hard and 20\% better than AlpacaEval 2.0 LC, while the Spearman coefficient is 0.7 more than the next best benchmark, showcasing a significant improvement in the usefulness of the benchmark. We further provide an open-source evaluation tool that enables fine-grained analysis of model performance across user-defined categories, offering valuable insights for practitioners. This work contributes to the ongoing effort to enhance the transparency, diversity, and effectiveness of LLM evaluation methodologies.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks

    cs.CL 2026-06 conditional novelty 7.0

    CoEval generates task-specific benchmarks by rotating models through teacher, student, and judge roles, then weights questions by discriminative power and judges by panel consensus to recover accurate model rankings w...

  2. LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models

    cs.CL 2025-08 conditional novelty 6.0

    LLMEval-Fair introduces a dynamic, contamination-resistant evaluation framework for LLMs based on a large question bank and validates it via a 30-month study of nearly 60 models showing performance ceilings and hidden...

  3. A Survey on LLM-as-a-Judge

    cs.CL 2024-11 unverdicted novelty 4.0

    A survey on LLM-as-a-Judge that reviews reliability strategies, proposes evaluation methods, and introduces a novel benchmark for assessing such systems.

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

    cs.CL 2024-12 accept novelty 3.0

    A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.