Related papers: Change And Cover: Last-Mile, Pull Request-Based Re…

Recent advances in automated test generation utilises language models to produce unit tests. While effective, language models tend to generate many incorrect tests with respect to both syntax and semantics. Although such incorrect tests can…

Unit testing plays a pivotal role in software development, improving software quality and reliability. However, generating effective test cases manually is time-consuming, prompting interest in unit testing research. Recently, Large…

Large Language Models (LLMs) are increasingly used to support software testing tasks, yet there is little evidence of their effectiveness for REST API testing in industrial settings. To address this gap, we replicate our earlier work on…

Recent advance in deep learning has led to the rapid adoption of machine learning-based NLP models in a wide range of applications. Despite the continuous gain in accuracy, backward compatibility is also an important aspect for industrial…

Integrating large language models (LLMs) as priors in reinforcement learning (RL) offers significant advantages but comes with substantial computational costs. We present a principled cache-efficient framework for posterior sampling with…

A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward…

Context: Due to the demand for strong algorithmic reasoning, complex logic implementation, and strict adherence to input/output formats and resource constraints, competitive programming generation by large language models (LLMs) is…

Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking…

Large language models (LLMs) have recently gained prominence in the field of software development, significantly boosting productivity and simplifying teamwork. Although prior studies have examined task-specific applications, the…

Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compared with standard supervised learning. Unfortunately, most…

Code completion aims to enhance programming productivity by predicting potential code based on the current programming context. Recently, pretrained language models (LMs) have become prominent in this field. Various approaches have been…

Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to train. This work aims to build data-efficient PRMs as…

LLM-assisted defect discovery has a precision crisis: plausible-but-wrong reports overwhelm maintainers and degrade credibility for real findings. We present Refute-or-Promote, an inference-time reliability pattern combining Stratified…

Code generation refers to automatically producing executable programs from user requirements. Recently, researchers have explored approaches to enhance the correctness of generated code with advanced large language models. Although…

The rise of reasoning models necessitates large-scale verifiable data, for which programming tasks serve as an ideal source. However, while competitive programming platforms provide abundant problems and solutions, high-quality test cases…

Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack…

Large language models (LLMs) have revolutionized artificial intelligence, but their increasing deployment across critical domains has raised concerns about their abnormal behaviors when faced with malicious attacks. Such vulnerability…

The rapid release of both language models and benchmarks makes it increasingly costly to evaluate every model on every dataset. In practice, models are often evaluated on different samples, making scores difficult to compare across studies.…

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for enhancing Large Language Models (LLMs) on complex reasoning tasks. However, existing methods suffer from an exploration dilemma: the sharply peaked initial…

Competitive programming, due to its high reasoning difficulty and precise correctness feedback, has become a key task for both training and evaluating the reasoning capabilities of large language models (LLMs). However, while a large amount…