Related papers: Validity-Preserving Delta Debugging via Generator …
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…
Modern IC complexity drives test pattern growth, with the majority of patterns targeting a small set of hard-to-detect (HTD) faults. This motivates new ATPG algorithms to improve test effectiveness specifically for HTD faults. This paper…
While large language models have made significant strides in code generation, the pass rate of the generated code is bottlenecked on subtle errors, often requiring human intervention to pass tests, especially for complex problems. Existing…
While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…
Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in…
Today, most automated test generators, such as search-based software testing (SBST) techniques focus on achieving high code coverage. However, high code coverage is not sufficient to maximise the number of bugs found, especially when given…
Logging statements are essential for software debugging and maintenance. However, existing approaches to automatic logging generation rely on static analysis and produce statements in a single pass without considering runtime behavior. They…
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios.…
The generation of synthetic inputs via simulators driven by search algorithms is essential for cost-effective testing of Deep Neural Network (DNN) components for safety-critical systems. However, in many applications, simulators are unable…
We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly leverages test inputs during synthesis. While prior approaches to program synthesis--whether based on natural language descriptions…
Minimizing failing test cases is an important pre-processing step on the path of debugging. If much of a test case that triggered a bug does not contribute to the actual failure, then the time required to fix the bug can increase…
Deep learning (DL) applications are prevalent nowadays as they can help with multiple tasks. DL libraries are essential for building DL applications. Furthermore, DL operators are the important building blocks of the DL libraries, that…
Large Language Models (LLMs) can translate natural language requirements into code, yet empirical analyses of representative models reveal that semantic errors-programs that compile but behave incorrectly-constitute the majority of observed…
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.e., performances…
Slow running or straggler tasks can significantly reduce computation speed in distributed computation. Recently, coding-theory-inspired approaches have been applied to mitigate the effect of straggling, through embedding redundancy in…
Abstract: Failing test case reduction can promote efficient debugging because a developer may not need to observe components that are not relevant to inducing failure. Failing test case reduction can also improve the efficiency of fault…
Given a list L of elements and a property that L exhibits, ddmin is a well-known test input minimization algorithm designed to automatically eliminate irrelevant elements from L. This algorithm is extensively adopted in test input…
Because query execution is the most crucial part of Inductive Logic Programming (ILP) algorithms, a lot of effort is invested in developing faster execution mechanisms. These execution mechanisms typically have a low-level implementation,…
Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel…
This paper introduces several techniques that improve the scalability of the deductive verification of data-level programs working on arrays and matrices. First of all, we introduce a technique to rewrite expressions with (nested)…