相关论文: Rationale Dataset and Analysis for the Commit Mess…

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Understanding narratives requires reading between the lines, which in turn, requires interpreting the likely causes and effects of events, even when they are not mentioned explicitly. In this paper, we introduce Cosmos QA, a large-scale…

Chain-of-thought (CoT) reasoning has enabled large language models (LLMs) to utilize additional computation through intermediate tokens to solve complex tasks. However, we posit that typical reasoning traces contain many redundant tokens,…

Change-based code review is used widely in industrial software development. Thus, research on tools that help the reviewer to achieve better review performance can have a high impact. We analyze one possibility to provide cognitive support…

Despite the potential of Machine learning (ML) to learn the behavior of malware, detect novel malware samples, and significantly improve information security (InfoSec) we see few, if any, high-impact ML techniques in deployed systems,…

The recent progress of artificial intelligence(AI) has shown great potentials for alleviating human burden in various complex tasks. From the view of software engineering, AI techniques can be seen in many fundamental aspects of…

Conventional commits provide a structured format for writing commit messages, which improves readability, software maintenance, and enables automation tools such as changelog generators and semantic versioning systems. Existing approaches…

Software architectures are usually meticulously designed to address multiple quality concerns and support long-term maintenance. However, due to the imbalance between the cost and value for developers to document design rationales (i.e.,…

Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their ability to reason about runtime behavior and understand the…

Commit messages have an important impact in software development, especially when working in large teams. Multiple developers who have a different style of writing may often be involved in the same project. For this reason, it may be…

Context. Code refactoring improves software quality without changing external behavior. Despite its advantages, its benefits are hindered by the considerable cost of time, resources, and continuous effort it demands. Aim. Understanding why…

Distilling explicit chain-of-thought reasoning paths has emerged as an effective method for improving the reasoning abilities of large language models (LLMs) across various tasks. However, when tackling complex tasks that pose significant…

Human communication is motivated: people speak, write, and create content with a particular communicative intent in mind. As a result, information that large language models (LLMs) and AI agents process is inherently framed by humans'…

The availability of open-source projects facilitates developers to contribute and collaborate on a wide range of projects. As a result, the developer community contributing to such open-source projects is also increasing. Many of the…

Every ML kernel ships with an implicit contract about what it computes. People rarely write the contract down. When two kernels disagree -- when a matmul on AMD produces a different gradient than the same matmul on NVIDIA, when a fused…

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…

Recent powerful pre-trained language models have achieved remarkable performance on most of the popular datasets for reading comprehension. It is time to introduce more challenging datasets to push the development of this field towards more…

Human computation refers to the outsourcing of computation tasks to human workers. It offers a new direction for solving a variety of problems and calls for innovative ways of managing human computation processes. The majority of human…

Recent work has shown how to prompt large language models with explanations to obtain strong performance on textual reasoning tasks, i.e., the chain-of-thought paradigm. However, subtly different explanations can yield widely varying…

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities…