相关论文: ReAssert: Deep Learning for Assert Generation

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards. Recent RLVR works that operate under the zero setting…

Legal professionals need to write analyses that rely on citations to relevant precedents, i.e., previous case decisions. Intelligent systems assisting legal professionals in writing such documents provide great benefits but are challenging…

Retrieval-Augmented Generation (RAG) mitigates factual errors and hallucinations in Large Language Models (LLMs) for question-answering (QA) by incorporating external knowledge. However, existing adaptive RAG methods rely on LLMs to predict…

Feature attribution methods (FAs), such as gradients and attention, are widely employed approaches to derive the importance of all input features to the model predictions. Existing work in natural language processing has mostly focused on…

This paper proposes an iterative inference algorithm for multi-hop explanation regeneration, that retrieves relevant factual evidence in the form of text snippets, given a natural language question and its answer. Combining multiple sources…

Implementing automated unit tests is an important but time-consuming activity in software development. To assist developers in this task, many techniques for automating unit test generation have been developed. However, despite this effort,…

Large language models can generate solutions to complex problems, but training them with reinforcement learning typically requires verifiable rewards that are expensive to create and not possible for all domains. We demonstrate that LLMs…

Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable answers. However, scaling rubric-based RL remains challenging: existing approaches often…

Bug datasets consisting of real-world bugs are important artifacts for researchers and programmers, which lay empirical and experimental foundation for various SE/PL research such as fault localization, software testing, and program repair.…

Coherence plays a critical role in producing a high-quality summary from a document. In recent years, neural extractive summarization is becoming increasingly attractive. However, most of them ignore the coherence of summaries when…

Testing in Continuous Integration (CI) involves test case prioritization, selection, and execution at each cycle. Selecting the most promising test cases to detect bugs is hard if there are uncertainties on the impact of committed code…

Transformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate…

Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, causing wasted computation, reduced readability, and…

Automatically crafting test scenarios for REST APIs helps deliver more reliable and trustworthy web-oriented systems. However, current black-box testing approaches rely heavily on the information available in the API's formal documentation,…

A major obstacle in reinforcement learning-based sentence generation is the large action space whose size is equal to the vocabulary size of the target-side language. To improve the efficiency of reinforcement learning, we present a novel…

Ensuring fairness in machine learning remains a significant challenge, as models often inherit biases from their training data. Generative models have recently emerged as a promising approach to mitigate bias at the data level while…

Reverse Engineering(RE) has been a fundamental task in software engineering. However, most of the traditional Java reverse engineering tools are strictly rule defined, thus are not fault-tolerant, which pose serious problem when noise and…

Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Generation (RAG) enriches prompts with external information, but…

Assessing the quality of outputs generated by generative models, such as large language models and vision language models, presents notable challenges. Traditional methods for evaluation typically rely on either human assessments, which are…

How to obtain a model with good interpretability and performance has always been an important research topic. In this paper, we propose rectified decision trees (ReDT), a knowledge distillation based decision trees rectification with high…