{"total":14,"rows":[{"id":"2511.11562","title":"PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning","created":"2025-11-14","cited_by_count":32,"area":null},{"id":"2602.05150","title":"GreekMMLU: A Native-Sourced Multitask Benchmark for Evaluating Language Models in Greek","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2505.24826","title":"LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal Text","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2602.16811","title":"Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2605.08437","title":"Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2601.01331","title":"AppellateGen: A Benchmark for Appellate Legal Judgment Generation","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2608.15630","title":"Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2608.18752","title":"GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2605.21076","title":"GradeLegal: Automated Grading for German Legal Cases","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.21274","title":"A Comparative Evaluation of Embeddings and LLMs in a Greek Book Publisher Setting - The CUP Dataset","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.17810","title":"Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.30327","title":"Do Small Models Use the Law You Give Them? Measuring Context Use on a Bilingual Bangladesh Legal Benchmark","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.09887","title":"When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.34800","title":"Pass or Fail? Evaluating LLMs on Two Greek Examination Benchmarks","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}