{"total":22,"rows":[{"id":"2503.10995","title":"TigerLLM - A Family of Bangla Large Language Models","created":"2025-03-14","cited_by_count":16,"area":null},{"id":"2509.09101","title":"TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla","created":"2025-09-11","cited_by_count":6,"area":null},{"id":"2507.15850","title":"3LM: Bridging Arabic, STEM, and Code through Benchmarking","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2410.17736","title":"MojoBench: Language Modeling and Benchmarks for Mojo","created":"2024-10-23","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2508.03678","title":"More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generation","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2412.08291","title":"Code LLMs: A Taxonomy-based Survey","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2509.16696","title":"Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2604.24929","title":"GAIA-v2-LILT: Multilingual Adaptation of Agent Benchmark beyond Translation","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2510.24450","title":"Charting the European LLM Benchmarking Landscape: A New Taxonomy and a Set of Best Practices","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2511.03498","title":"BanglaSTEM: A Parallel Corpus for Technical Domain Bangla-English Translation","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2601.03708","title":"MHRC-Bench: A Multilingual Hardware Repository-Level Code Completion benchmark","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2602.02440","title":"Large Language Models for Mental Health: A Multilingual Evaluation","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.07083","title":"Rethinking Scientific Modeling: Toward Physically Consistent and Simulation-Executable Programmatic Generation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2505.24324","title":"SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2509.22768","title":"ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.07382","title":"Retriv at BLP-2025 Task 2: Test-Driven Feedback-Guided Framework for Bangla-to-Python Code Generation","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2511.12823","title":"Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpreter","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2511.16787","title":"NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2512.19122","title":"BanglaForge: LLM Collaboration with Self-Refinement for Bangla Code Generation","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2605.01224","title":"Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2609.06527","title":"ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}