5 papers
Beyond Resolved Rate: A Non-Functional Quality Study
Xin Sun, Daniel Ståhl, Kristian Sandahl +1
Repository-level coding benchmarks typically measure progress in model capability by comparing the resolved rates of later and earlier models. However, this focus overlooks whether…
Seeing the Reasoning: How LLM Rationales Influence User Trust and Decision-Making in Factual Verification Tasks
Xin Sun, Shu Wei, Jos A Bosch +3
Large Language Models (LLMs) increasingly show reasoning rationales alongside their answers, turning "reasoning" into a user-interface element. While step-by-step rationales are ty…
Patch Validation in Automated Vulnerability Repair
Zheng Yu, Wenxuan Shi, Xinqian Sun +3
Automated Vulnerability Repair (AVR) systems, especially those leveraging large language models (LLMs), have demonstrated promising results in patching vulnerabilities -- that is,…
BandFuzz: An ML-powered Collaborative Fuzzing Framework
Wenxuan Shi, Hongwei Li, Jiahao Yu +3
Collaborative fuzzing combines multiple individual fuzzers and dynamically chooses appropriate combinations for different programs. Unlike individual fuzzers that rely on specific…
A Large Language Model Approach to Identify Flakiness in C++ Projects
Xin Sun, Daniel Ståhl, Kristian Sandahl
The role of regression testing in software testing is crucial as it ensures that any new modifications do not disrupt the existing functionality and behaviour of the software syste…