{"total":21,"rows":[{"id":"2505.13360","title":"What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts","created":"2025-05-19","cited_by_count":32,"area":null},{"id":"2409.12447","title":"Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts","created":"2024-09-19","cited_by_count":19,"area":null},{"id":"2407.09435","title":"MUSCLE: A Model Update Strategy for Compatible LLM Evolution","created":"2024-07-12","cited_by_count":15,"area":null},{"id":"2510.25506","title":"Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering Studies","created":"2025-10-29","cited_by_count":12,"area":null},{"id":"2410.12071","title":"Beyond the Comfort Zone: Emerging Solutions to Overcome Challenges in Integrating LLMs into Software Products","created":"2024-10-15","cited_by_count":11,"area":null},{"id":"2503.05070","title":"PromptPex: Automatic Test Generation for Language Model Prompts","created":"2025-03-07","cited_by_count":9,"area":null},{"id":"2604.00136","title":"ParetoBandit: Budget-Paced Adaptive Routing for Non-Stationary LLM Serving","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2409.06725","title":"DefectTwin: When LLM Meets Digital Twin for Railway Defect Inspection","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2410.20791","title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2504.12335","title":"You've Changed: Detecting Modification of Black-Box Large Language Models","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2604.27789","title":"Test Before You Deploy: Governing Updates in the LLM Supply Chain","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2409.09261","title":"What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data Slicing","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2505.10640","title":"The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2506.13384","title":"Delving Into the Psychology of Machines: Exploring the Structure of Self-Regulated Learning via LLM-Generated Survey Responses","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2507.19390","title":"ReCatcher: Towards LLMs Regression Testing for Code Generation","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2604.16304","title":"Results-Actionability Gap: Understanding How Practitioners Evaluate LLM Products in the Wild","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2608.17719","title":"What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.20918","title":"UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.28592","title":"A collective capability boundary in frontier large language models on guideline-conformant and case-specific oncology decision-making","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.30074","title":"How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.19084","title":"Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}