{"total":20,"rows":[{"id":"2602.12247","title":"ExtractBench: A Benchmark and Evaluation Methodology for Complex Structured Extraction","created":"2026-02-12","cited_by_count":9,"area":null},{"id":"2604.15597","title":"LLMs Corrupt Your Documents When You Delegate","created":"2026-04-17","cited_by_count":9,"area":null},{"id":"2604.22937","title":"AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs","created":"2026-04-24","cited_by_count":7,"area":null},{"id":"2512.23712","title":"STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability","created":"2025-11-27","cited_by_count":5,"area":null},{"id":"2601.06341","title":"Evaluating Robustness of Large Language Models in Enterprise Applications: Benchmarks for Perturbation Consistency Across Formats and Languages","created":"2026-01-09","cited_by_count":5,"area":null},{"id":"2604.25359","title":"The Structured Output Benchmark: A Multi-Source Benchmark for Evaluating Structured Output Quality in Large Language Models","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2512.14336","title":"Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2510.21970","title":"Performance Trade-offs of Optimizing Small Language Models for E-Commerce","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2602.06384","title":"FMBench: Adaptive Large Language Model Output Formatting","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.08872","title":"Large Language Models for Geolocation Extraction in Humanitarian Crisis Response","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2609.17699","title":"NeMo Data Designer: An Extensible Framework for Multimodal Synthetic Data Generation","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2509.25922","title":"DeepJSONEval: Benchmarking Complex Nested JSON Data Mining for Large Language Models","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2603.23532","title":"Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2605.29986","title":"Accelerating Constrained Decoding with Token Space Compression","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2608.14370","title":"A Hybrid LLM-Based Framework for Automated Security Annotation Generation in Business Process Models","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.15223","title":"TRACE-BN: Transferring Bangla-English Tutoring Behavior to a Sub-1B Offline Language Model","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.06993","title":"LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.10016","title":"MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.22537","title":"EvidenT: Building Trustworthy Enterprise Assistants through Evidence Groundedness and Traceability","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2610.19693","title":"ReFormBench: Benchmarking the Stability of Response-Conditioned Format Correction in Large Language Models","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}