Software Engineering

How to Data in Datathons NeurIPS 2023 Improving NER Research Workflows with SeqScore EMNLP 2023 Improving Transformer-based Program Repair Model through False Behavior Diagnosis EMNLP 2023 InstructExcel: A Benchmark for Natural Language Instruction in Excel EMNLP 2023 Intervention-Based Alignment of Code Search with Execution Feedback EMNLP 2023 Kani: A Lightweight and Highly Hackable Framework for Building Language Model Applications EMNLP 2023 Large Language Models of Code Fail at Completing Code with Potential Bugs NeurIPS 2023 Mass-Producing Failures of Multimodal Systems with Language Models NeurIPS 2023 Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context NeurIPS 2023 Nkululeko: Machine Learning Experiments on Speaker Characteristics Without Programming Interspeech 2023 PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis NeurIPS 2023 Push-Button Reliability Testing for Cloud-Backed Applications with Rainmaker NSDI 2023 Python Code Generation by Asking Clarification Questions ACL 2023 Ranking LLM-Generated Loop Invariants for Program Verification EMNLP 2023 Relational Debugging --- Pinpointing Root Causes of Performance Problems OSDI 2023 Renku: a platform for sustainable data science NeurIPS 2023 Repair Is Nearly Generation: Multilingual Program Repair with LLMs AAAI 2023 Robust Code Summarization EMNLP 2023 Robust Scheduling with GFlowNets ICLR 2023 R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents ICML 2023 Scaling Up Models and Data with t5x and seqio JMLR 2023 SQLFlow: An Extensible Toolkit Integrating DB and AI JMLR 2023 Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions ICLR 2023 SUT: Active Defects Probing for Transcompiler Models EMNLP 2023 Synthesizing Runtime Programmable Switch Updates NSDI 2023