{"total":17,"rows":[{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2405.09798","title":"Many-Shot In-Context Learning in Multimodal Foundation Models","created":"2024-05-16","cited_by_count":67,"area":null},{"id":"2403.07794","title":"Fine-tuning Large Language Models with Sequential Instructions","created":"2024-03-12","cited_by_count":20,"area":null},{"id":"2406.19999","title":"The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models","created":"2024-06-28","cited_by_count":18,"area":null},{"id":"2412.08587","title":"Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning","created":"2024-12-11","cited_by_count":7,"area":null},{"id":"2406.10786","title":"Evaluating LLMs with Multiple Problems at once","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2411.10163","title":"Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions","created":"2024-11-15","cited_by_count":5,"area":null},{"id":"2502.19160","title":"Detecting Linguistic Indicators for Stereotype Assessment with Large Language Models","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2505.09027","title":"Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation","created":"2025-05-13","cited_by_count":5,"area":null},{"id":"2506.02480","title":"ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2603.22608","title":"Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2512.08646","title":"QSTN: A Modular Framework for Robust Questionnaire Inference with Large Language Models","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2604.15827","title":"UsefulBench: Towards Decision-Useful Information as a Target for Information Retrieval","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2509.18123","title":"SPADE: A Large Language Model Framework for Soil Moisture Pattern Recognition and Anomaly Detection in Precision Agriculture","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2601.14429","title":"Measuring the State of Open Science in Transportation Using Large Language Models","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2604.26351","title":"A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2610.12762","title":"Faithful and Complete LLM-Assisted Automated Construction of Hierarchical Hardware Knowledge Graphs","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}