{"total":15,"rows":[{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2406.19783","title":"NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations","created":"2024-06-28","cited_by_count":20,"area":null},{"id":"2402.05980","title":"Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2406.03993","title":"Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2312.14856","title":"Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code","created":"2023-12-22","cited_by_count":9,"area":null},{"id":"2502.17657","title":"StatLLM: A Dataset for Evaluating the Performance of Large Language Models in Statistical Analysis","created":"2025-02-24","cited_by_count":8,"area":null},{"id":"2510.12255","title":"Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs","created":"2025-10-14","cited_by_count":8,"area":null},{"id":"2503.22851","title":"RobuNFR: Evaluating the Robustness of Large Language Models on Non-Functional Requirements Aware Code Generation","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2506.22776","title":"Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2505.08303","title":"Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2605.29737","title":"Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2502.08180","title":"Enhancing LLM Character-Level Manipulation via Divide and Conquer","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2408.09134","title":"Better Python Programming for all: With the focus on Maintainability","created":"2024-08-17","cited_by_count":0,"area":null}],"next_cursor":null}