{"total":14,"rows":[{"id":"2503.02296","title":"Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting","created":"2025-03-04","cited_by_count":7,"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":"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":"2506.10204","title":"Code Roulette: How Prompt Variability Affects LLM Code Generation","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2604.24703","title":"Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis","created":"2026-04-27","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":"2505.21224","title":"A Representation Level Analysis of NMT Model Robustness to Grammatical Errors","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2509.13680","title":"Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variations","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2601.03988","title":"Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2604.23135","title":"Characterizing Paraphrase-Induced Failures in Lean 4 Autoformalization","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2606.09484","title":"Detecting Differences Is Not Understanding Structure: Large Language Models Fail at Graph Isomorphism","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2504.08852","title":"ML For Hardware Design Interpretability: Challenges and Opportunities","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2608.12771","title":"Memorization Diagnostics for Code LLMs Should be Scale-Aware","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.32172","title":"Noisy Test-Time Reinforcement Learning for Code LLMs","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}