{"total":23,"rows":[{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2510.17281","title":"MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems","created":"2025-10-20","cited_by_count":61,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"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":"2506.00694","title":"Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM-Generated 3-ply Case-Based Legal Arguments","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2507.21773","title":"AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2605.10186","title":"LegalCiteBench: Evaluating Citation Reliability in Legal Language Models","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2503.04305","title":"Computational Law: Datasets, Benchmarks, and Ontologies","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2505.19667","title":"LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2505.21958","title":"Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.06060","title":"Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2511.04705","title":"POLIS-Bench: Towards Multi-Dimensional Evaluation of LLMs for Bilingual Policy Tasks in Governmental Scenarios","created":"2025-11-04","cited_by_count":1,"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":"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":"2606.08932","title":"From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2508.18636","title":"LaQual: An Automated Framework for LLM App Quality Evaluation","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2601.09972","title":"Chinese Labor Law Large Language Model Benchmark","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2604.17543","title":"PoliLegalLM: A Technical Report on a Large Language Model for Political and Legal Affairs","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2607.24449","title":"Evaluating RAG for French immigration law: a benchmark and baseline study","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.10268","title":"Toward Human Rights Benchmarking for LLMs: A Pilot Methodology","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.07784","title":"xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.05966","title":"HuatuoGPT-3: RL-Only Domain Adaptation from Base Models","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}