{"total":16,"rows":[{"id":"2601.16669","title":"PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice","created":"2026-01-23","cited_by_count":15,"area":null},{"id":"2605.26329","title":"JobBench: Aligning Agent Work With Human Will","created":"2026-05-25","cited_by_count":10,"area":null},{"id":"2511.22978","title":"ShoppingComp: Are LLMs Really Ready for Your Shopping Cart?","created":"2025-11-28","cited_by_count":9,"area":null},{"id":"2605.23454","title":"ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning","created":"2026-05-22","cited_by_count":4,"area":null},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2601.15267","title":"Evaluation of Large Language Models in Legal Applications: Challenges, Methods, and Future Directions","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2603.01343","title":"PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.10002","title":"SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2605.11978","title":"On Predicting the Post-training Potential of Pre-trained LLMs","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.27047","title":"NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.16122","title":"CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.22559","title":"ExecRubrics: Executable Tool-Augmented Rubrics for Verifiable and Efficient Long-Form Evaluation","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.33467","title":"A Cheap Verifier is Good Enough: LLM Post-training is Robust to Erroneous Rewards","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35744","title":"FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37322","title":"Mubric: Mutation Testing-Guided Rubric Generation for LLM Evaluation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.19138","title":"MA-Bench: Measuring Operational Planning in Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}