Related papers: Exploring the Effectiveness of Abstract Syntax Tre…

Large Language Models (LLMs) often struggle to maintain their original performance when faced with semantically coherent but task-irrelevant contextual information. Although prior studies have explored this issue using fixed-template or…

In Computer Science (CS) education, understanding factors contributing to students' programming difficulties is crucial for effective learning support. By identifying specific issues students face, educators can provide targeted assistance…

Code writing is repetitive and predictable, inspiring us to develop various code intelligence techniques. This survey focuses on code search, that is, to retrieve code that matches a given query by effectively capturing the semantic…

We study the problem of learning differentiable functions expressed as programs in a domain-specific language. Such programmatic models can offer benefits such as composability and interpretability; however, learning them requires…

This paper presents a hybrid system for intuitive item similarity search that combines a Large Language Model (LLM) with a custom K-Nearest Neighbors (KNN) algorithm. Unlike black-box dense vector systems, this architecture provides…

Predictive models are fundamental to engineering reliable software systems. However, designing conservative, computable approximations for the behavior of programs (static analyses) remains a difficult and error-prone process for modern…

The determination of block-entropies is a well established method for the investigation of discrete data, also called symbols (7). There is a large variety of such symbolic sequences, ranging from texts written in natural languages,…

Code cloning, the duplication of code fragments, is common in software development. While some reuse aids productivity, excessive cloning hurts maintainability and introduces bugs. Hence, automatic code clone detection is vital. Meanwhile,…

This paper introduces a novel code-to-code search technique that enhances the performance of Large Language Models (LLMs) by including both static and dynamic features as well as utilizing both similar and dissimilar examples during…

Code flaws or vulnerabilities are prevalent in software systems and can potentially cause a variety of problems including deadlock, information loss, or system failure. A variety of approaches have been developed to try and detect the most…

For a given software bug report, identifying an appropriate developer who could potentially fix the bug is the primary task of a bug triaging process. A bug title (summary) and a detailed description is present in most of the bug tracking…

Scene text recognition (STR) is very challenging due to the diversity of text instances and the complexity of scenes. The community has paid increasing attention to boost the performance by improving the pre-processing image module, like…

Large language models (LLMs) are increasingly deployed for understanding large codebases, but whether they understand operational semantics of long code context or rely on pattern matching shortcuts remains unclear. We distinguish between…

Predicting program properties such as names or expression types has a wide range of applications. It can ease the task of programming and increase programmer productivity. A major challenge when learning from programs is $\textit{how to…

Tree-based models have proven to be an effective solution for web ranking as well as other problems in diverse domains. This paper focuses on optimizing the runtime performance of applying such models to make predictions, given an…

One of the most challenging goals in designing intelligent systems is empowering them with the ability to synthesize programs from data. Namely, given specific requirements in the form of input/output pairs, the goal is to train a machine…

Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb--a hierarchy-aware framework--to organize sentence…

Automated agent workflows can enhance the problem-solving ability of large language models (LLMs), but common search strategies rely on stochastic exploration and often traverse implausible branches. This occurs because current pipelines…

Protein retrieval, which targets the deconstruction of the relationship between sequences, structures and functions, empowers the advancing of biology. Basic Local Alignment Search Tool (BLAST), a sequence-similarity-based algorithm, has…

In this work, we apply anomaly detection to source code and bytecode to facilitate the development of a programming language and its compiler. We define anomaly as a code fragment that is different from typical code written in a particular…