Related papers: QiMeng-NeuComBack: Self-Evolving Translation from …

Transformer-based large language models (LLMs) are constrained by the fixed context window of the underlying transformer architecture, hindering their ability to produce long and coherent outputs. Memory-augmented LLMs are a promising…

Large Language Models (LLMs) have emerged as a powerful tool in advancing the Text-to-SQL task, significantly outperforming traditional methods.Nevertheless, as a nascent research field, there is still no consensus on the optimal prompt…

The rapid evolution of software libraries creates a significant challenge for Large Language Models (LLMs), whose static parametric knowledge often becomes stale post-training. While retrieval-augmented generation (RAG) is commonly used to…

Large Language Models (LLMs) have achieved remarkable capabilities, yet their improvement methods remain fundamentally constrained by human design. We present Self-Developing, a framework that enables LLMs to autonomously discover,…

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…

We introduce DafnyCOMP, a benchmark for evaluating large language models (LLMs) on compositional specification generation in Dafny. Unlike prior benchmarks that focus on single-function tasks, DafnyCOMP targets programs composed of multiple…

Large Language Models (LLMs) are widely adopted for assisting in software development tasks, yet their performance evaluations have narrowly focused on the functional correctness of generated code. Human programmers, however, require…

Logs are ubiquitous digital footprints, playing an indispensable role in system diagnostics, security analysis, and performance optimization. The extraction of actionable insights from logs is critically dependent on the log parsing…

Effective prompt engineering is critical to realizing the promised productivity gains of large language models (LLMs) in knowledge-intensive tasks. Yet, many users struggle to craft prompts that yield high-quality outputs, limiting the…

Large Language Models (LLMs) excel at general code generation, but their performance drops sharply in enterprise settings that rely on internal private libraries absent from public pre-training corpora. While Retrieval-Augmented Generation…

Hardware accelerators, in particular accelerators for tensor processing, have many potential application domains. However, they currently lack the software infrastructure to support the majority of domains outside of deep learning.…

Traditional auto-parallelizing compilers, reliant on rigid heuristics, struggle with the complexity of modern heterogeneous systems. This paper presents a comprehensive evaluation of small (approximately 1B parameter) language-model-driven…

Natural Language Processing (NLP) systems are increasingly taking the form of sophisticated modular pipelines, e.g., Retrieval Augmented Generation (RAG), where each module may involve a distinct Language Model (LM) and an associated prompt…

Large Language Models (LLMs) are showing remarkable performance in generating source code, yet the generated code often has issues like compilation errors or incorrect code. Researchers and developers often face wasted effort in…

Large language models (LLMs) have achieved impressive performance on code generation. Although prior studies enhanced LLMs with prompting techniques and code refinement, they still struggle with complex programming problems due to rigid…

Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble…

Generating performant executables from high level languages is critical to software performance across a wide range of domains. Modern compilers perform this task by passing code through a series of well-studied optimizations at…

Goal-oriented de novo molecule design, namely generating molecules with specific property or substructure constraints, is a crucial yet challenging task in drug discovery. Existing methods, such as Bayesian optimization and reinforcement…

Large language models (LLMs) have achieved remarkable progress in solving various natural language processing tasks due to emergent reasoning abilities. However, LLMs have inherent limitations as they are incapable of accessing up-to-date…

Automated analysis for engineering structures offers considerable potential for boosting efficiency by minimizing repetitive tasks. Although AI-driven methods are increasingly common, no systematic framework yet leverages Large Language…