Scholarlink

<p>This study provides an empirical assessment of whether current large language models (LLMs) can pass the written part of the official qualifying examination for membership in Poland’s National Appeal Chamber (Krajowa Izba Odwoławcza). The authors examine two related ideas: using LLM as actual exam candidates and applying the ’LLM-as-a-judge’ approach, in which model-generated answers are automatically evaluated by other models. The paper describes the structure of the exam, which includes a single-choice knowledge test on public procurement law and a written judgment, and presents the hybrid information recovery and extraction pipeline built to support the models. Several LLMs (including GPT-4.1, Claude 4 Sonnet and Bielik-11B-v2.6) were tested in closed-book and various Retrieval-Augmented Generation settings. The results show that although the models achieved satisfactory scores in the knowledge test, none met the passing threshold in the practical written part, and the evaluations of the ‘LLM-as-a-judge’ often diverged from the judgments of the official examining committee. The authors highlight key limitations: susceptibility to hallucinations, incorrect citation of legal provisions, weaknesses in logical argumentation, and the need for close collaboration between legal experts and technical teams. The findings indicate that, despite rapid technological progress, LLMs (specifically the non-reasoning ones) cannot yet replace human judges or independent examiners in Polish public procurement adjudication.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

LLM-as-a-judge is bad, based on AI attempting the exam qualifying for the member of the Polish National Board of Appeal

  • 期刊论文

  • 发表日期：

    2026年3月9日

查看全文
  • Michał Karp,
  • Anna Kubaszewska,
  • Magdalena Król,
  • Robert Król,
  • Witold Wydmański,
  • Aleksander Smywiński-Pohl,
  • Mateusz Szymański

摘要

This study provides an empirical assessment of whether current large language models (LLMs) can pass the written part of the official qualifying examination for membership in Poland’s National Appeal Chamber (Krajowa Izba Odwoławcza). The authors examine two related ideas: using LLM as actual exam candidates and applying the ’LLM-as-a-judge’ approach, in which model-generated answers are automatically evaluated by other models. The paper describes the structure of the exam, which includes a single-choice knowledge test on public procurement law and a written judgment, and presents the hybrid information recovery and extraction pipeline built to support the models. Several LLMs (including GPT-4.1, Claude 4 Sonnet and Bielik-11B-v2.6) were tested in closed-book and various Retrieval-Augmented Generation settings. The results show that although the models achieved satisfactory scores in the knowledge test, none met the passing threshold in the practical written part, and the evaluations of the ‘LLM-as-a-judge’ often diverged from the judgments of the official examining committee. The authors highlight key limitations: susceptibility to hallucinations, incorrect citation of legal provisions, weaknesses in logical argumentation, and the need for close collaboration between legal experts and technical teams. The findings indicate that, despite rapid technological progress, LLMs (specifically the non-reasoning ones) cannot yet replace human judges or independent examiners in Polish public procurement adjudication.