{"total":93,"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":"2408.04667","title":"Non-Determinism of \"Deterministic\" LLM Settings","created":"2024-08-06","cited_by_count":92,"area":null},{"id":"2311.08596","title":"Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment","created":"2023-11-14","cited_by_count":77,"area":null},{"id":"2402.18225","title":"CogBench: a large language model walks into a psychology lab","created":"2024-02-28","cited_by_count":63,"area":null},{"id":"2506.09501","title":"Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference","created":"2025-06-11","cited_by_count":53,"area":null},{"id":"2403.14541","title":"EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling","created":"2024-03-21","cited_by_count":45,"area":null},{"id":"2312.17476","title":"Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameters","created":"2023-12-29","cited_by_count":32,"area":null},{"id":"2409.08775","title":"What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use","created":"2024-09-13","cited_by_count":24,"area":null},{"id":"2502.15844","title":"Hallucination Detection in Large Language Models with Metamorphic Relations","created":"2025-02-20","cited_by_count":24,"area":null},{"id":"2408.08333","title":"CodeMirage: Hallucinations in Code Generated by Large Language Models","created":"2024-08-14","cited_by_count":23,"area":null},{"id":"2312.06056","title":"METAL: Metamorphic Testing Framework for Analyzing Large-Language Model Qualities","created":"2023-12-11","cited_by_count":20,"area":null},{"id":"2505.16222","title":"Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","created":"2025-05-22","cited_by_count":18,"area":null},{"id":"2404.03398","title":"Scaling Up Video Summarization Pretraining with Large Language Models","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2509.11252","title":"Exploring the Potential of Diffusion Large Language Models in Code Generation","created":"2025-09-14","cited_by_count":16,"area":null},{"id":"2310.06680","title":"Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach","created":"2023-10-10","cited_by_count":15,"area":null},{"id":"2410.09112","title":"HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction","created":"2024-10-10","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":"2411.00585","title":"Fairness Testing of Large Language Models in Role-Playing","created":"2024-11-01","cited_by_count":11,"area":null},{"id":"2309.16573","title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2511.19933","title":"Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications","created":"2025-11-25","cited_by_count":10,"area":null},{"id":"2403.03997","title":"Guiding Enumerative Program Synthesis with Large Language Models","created":"2024-03-06","cited_by_count":9,"area":null},{"id":"2409.00921","title":"Statically Contextualizing Large Language Models with Typed Holes","created":"2024-09-02","cited_by_count":9,"area":null},{"id":"2402.15943","title":"Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware","created":"2024-02-25","cited_by_count":6,"area":null},{"id":"2406.06864","title":"Validating LLM-Generated Programs with Metamorphic Prompt Testing","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2410.07391","title":"The Cognitive Capabilities of Generative AI: A Comparative Analysis with Human Benchmarks","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2403.08430","title":"Search-based Optimisation of LLM Learning Shots for Story Point Estimation","created":"2024-03-13","cited_by_count":5,"area":null},{"id":"2501.11354","title":"Towards Advancing Code Generation with Large Language Models: A Research Roadmap","created":"2025-01-20","cited_by_count":5,"area":null},{"id":"2401.17626","title":"Generative AI to Generate Test Data Generators","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2407.09974","title":"To what extent is ChatGPT useful for language teacher lesson plan creation?","created":"2024-04-25","cited_by_count":4,"area":null},{"id":"2410.07793","title":"Do Current Language Models Support Code Intelligence for R Programming Language?","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2502.20825","title":"LADs: Leveraging LLMs for AI-Driven DevOps","created":"2025-02-28","cited_by_count":4,"area":null},{"id":"2604.05150","title":"Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2607.13304","title":"Where Does the Noise Come From? A Variance-Components Decomposition of Non-Determinism in LLM Brand Answers","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2401.07994","title":"Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2402.01723","title":"An Empirical Study on Large Language Models in Accuracy and Robustness under Chinese Industrial Scenarios","created":"2024-01-27","cited_by_count":3,"area":null},{"id":"2407.21227","title":"TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2409.15324","title":"Cognitive phantoms in LLMs through the lens of latent variables","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2509.09705","title":"The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2602.05883","title":"A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2312.13521","title":"Preparing to Integrate Generative Pretrained Transformer Series 4 models into Genetic Variant Assessment Workflows: Assessing Performance, Drift, and Nondeterminism Characteristics Relative to Classifying Functional Evidence in Literature","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2408.02964","title":"Accuracy and Consistency of LLMs in the Registered Dietitian Exam: The Impact of Prompt Engineering and Knowledge Retrieval","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2508.11257","title":"Hallucination in LLM-Based Code Generation: An Automotive Case Study","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2508.14288","title":"Measuring LLM Code Generation Stability via Structural Entropy","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2510.03795","title":"Investigating LLM Variability in Personalized Conversational Information Retrieval","created":"2025-10-04","cited_by_count":2,"area":null},{"id":"2602.08565","title":"Agent-Supported Foresight for AI Systemic Risks: AI Agents for Breadth, Experts for Judgment","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2604.22411","title":"Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2312.17353","title":"Towards Auto-Modeling of Formal Verification for NextG Protocols: A Multimodal cross- and self-attention Large Language Model Approach","created":"2023-12-28","cited_by_count":1,"area":null},{"id":"2412.10587","title":"Evaluation of GPT-4o and GPT-4o-mini's Vision Capabilities for Compositional Analysis from Dried Solution Drops","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2501.00691","title":"Labels Generated by Large Language Models Help Measure People's Empathy in Vitro","created":"2025-01-01","cited_by_count":1,"area":null},{"id":"2501.06461","title":"Assessing instructor-AI cooperation for grading essay-type questions in an introductory sociology course","created":"2025-01-11","cited_by_count":1,"area":null},{"id":"2504.16485","title":"On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2504.17531","title":"Towards Machine-Generated Code for the Resolution of User Intentions","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2505.15088","title":"Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.19353","title":"Architectures of Error: A Philosophical Inquiry into AI and Human Code Generation","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2506.17367","title":"Cash or Comfort? How LLMs Value Your Inconvenience","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2507.23087","title":"On LLM-Assisted Generation of Smart Contracts from Business Processes","created":"2025-07-30","cited_by_count":1,"area":null},{"id":"2510.02679","title":"Automated Constraint Specification for Job Scheduling by Regulating Generative Model with Domain-Specific Representation","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2512.23711","title":"CAT: A Metric-Driven Framework for Analyzing the Consistency-Accuracy Relation of LLMs under Controlled Input Variations","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2601.05579","title":"RISE: Rule-Driven SQL Dialect Translation via Query Reduction","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2601.15728","title":"Benchmarking Text-to-Python against Text-to-SQL: The Impact of Explicit Logic and Ambiguity","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2602.06190","title":"Generics in science communication: Misaligned interpretations across laypeople, scientists, and large language models","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2604.16756","title":"Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2606.21619","title":"The Alignment Problem in Constrained Code Generation","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2609.35873","title":"More Programs or More Rolls? Separating Coverage from Specialization in LLM Harnesses","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2408.14834","title":"Strategic Optimization and Challenges of Large Language Models in Object-Oriented Programming","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2503.11662","title":"Lorecast: Layout-Aware Performance and Power Forecasting from Natural Language","created":"2025-02-14","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":"2508.06017","title":"Position: Intelligent Coding Systems Should Write Programs with Justifications","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2509.07869","title":"Are Humans as Brittle as Large Language Models?","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.09226","title":"Constructing a Question-Answering Simulator through the Distillation of LLMs","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2510.08576","title":"Comparative Analysis of Large Language Models for the Machine-Assisted Resolution of User Intentions","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2510.20584","title":"Automated Coding of Communication Data Using ChatGPT: Consistency Across Subgroups","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.14002","title":"FlakyGuard: Automatically Fixing Flaky Tests at Industry Scale","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.19481","title":"A Dataset and Preliminary Study of Using GPT-5 for Code-change Impact Analysis","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2601.21605","title":"Age Matters: Analyzing Age-Related Discussions in App Reviews","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.19826","title":"Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.24544","title":"STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.21465","title":"Leveraging LLMs for Grammar Adaptation: A Study on Metamodel-Grammar Co-Evolution","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.12273","title":"Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.14816","title":"Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.19949","title":"SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation Data","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.00739","title":"EduPluginBench: Executable Assurance for AI-Generated Educational Plugins","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.06041","title":"LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.07148","title":"A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturing","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.21208","title":"Specification Portability Across LLM Development Agents: Cross-Agent Compatibility in Specification-Driven Software Migration","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.04198","title":"Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.12286","title":"T-GADE: Thermodynamical Generative-AI-Driven Evolution of LLM Artifacts","created":"2026-09-10","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":"2609.30749","title":"ORCA: Evaluating LLMs on Data Science Code Translation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.37294","title":"SafeLLM4SE: Statistical Evaluation and Reporting for LLM-based Software Engineering Systems","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00654","title":"When More Data Is Not Enough: The Context-Sufficiency Frontier in Generative AI Personalization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02839","title":"To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.19608","title":"Twenty Days Later: A Pre-Registered Test of History-Based Forecasts of Brand Mentions in Gemini Answers","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}