Related papers: Debug Like a Human: Scaling LLM-based Fault Locali…
Fuzzing has become a commonly used approach to identifying bugs in complex, real-world programs. However, interpreters are notoriously difficult to fuzz effectively, as they expect highly structured inputs, which are rarely produced by most…
Recent efforts to improve the performance of neural network (NN) accelerators that meet today's application requirements have given rise to a new trend of logic-based NN inference relying on fixed-function combinational logic (FFCL). This…
Federated learning (FL) is a distributed machine learning (ML) paradigm, allowing multiple clients to collaboratively train shared machine learning (ML) models without exposing clients' data privacy. It has gained substantial popularity in…
Emulator is widely used to build dynamic analysis frameworks due to its fine-grained tracing capability, full system monitoring functionality, and scalability of running on different operating systemsand architectures. However, whether the…
Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with…
Bug localization is a tedious activity in the bug fixing process in which a software developer tries to locate bugs in the source code described in a bug report. Since this process is time-consuming and requires additional knowledge about…
As the adoption of Deep Learning (DL) systems continues to rise, an increasing number of approaches are being proposed to test these systems, localise faults within them, and repair those faults. The best attestation of effectiveness for…
Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but over-edited solutions during debugging. To evaluate how far LLMs are from precise…
Deep neural networks (DNNs) are susceptible to bugs, just like other types of software systems. A significant uptick in using DNN, and its applications in wide-ranging areas, including safety-critical systems, warrant extensive research on…
Large language model (LLM) services have become an integral part of search, assistance, and decision-making applications. However, unlike traditional web or microservices, the hardware and software stack enabling LLM inference deployment is…
Bug reproduction is a critical developer activity that is also challenging to automate, as bug reports are often in natural language and thus can be difficult to transform to test cases consistently. As a result, existing techniques mostly…
Software defects consume 40% of the total budget in software development and cost the global economy billions of dollars every year. Unfortunately, despite the use of many software quality assurance (SQA) practices in software development…
Automated issue fixing is a critical task in software debugging and has recently garnered significant attention from academia and industry. However, existing fixing techniques predominantly focus on the repair phase, often overlooking the…
Debugging is an essential skill when learning to program, yet its instruction and emphasis often vary widely across introductory courses. In the era of code-generating large language models (LLMs), the ability for students to reason about…
Static analysis plays a crucial role in software vulnerability detection, yet faces a persistent precision-scalability tradeoff. In large codebases like the Linux kernel, traditional static analysis tools often generate excessive false…
In this paper, we first show that increases in beam size, even for small-sized LLMs (1B-7B params), require extensive GPU usage, leading to up to 80% of recurring crashes due to memory overloads in LLM-based APR. Seemingly simple solutions…
Bug localization, which is used to help programmers identify the location of bugs in source code, is an essential task in software development. Researchers have already made efforts to harness the powerful deep learning (DL) techniques to…
Large Language Models (LLMs) are increasingly deployed to resolve real-world GitHub issues. However, despite their potential, the specific failure modes of these models in complex repair tasks remain poorly understood. To characterize how…
Large language models (LLMs) have shown promise in software engineering, yet their effectiveness for binary analysis remains unexplored. We present the first comprehensive evaluation of commercial LLMs for assembly code deobfuscation.…
We present that hierarchical LLM reasoning via scaling thought templates can effectively optimize the reasoning search space and outperform the mathematical reasoning capabilities of powerful LLMs like OpenAI o1-preview and DeepSeek V3. We…