相关论文: MFTCoder: Boosting Code LLMs with Multitask Fine-T…

Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capability of large language models (LLMs) and also benefit downstream tasks such as code…

Finetuning large language models (LLMs) is essential for task adaptation, yet today's serving stacks isolate inference and finetuning on separate GPU clusters -- wasting resources and under-utilizing hardware. We introduce FlexLLM, the…

The rapid advancements in large language models (LLMs) have greatly expanded the potential for automated code-related tasks. Two primary methodologies are used in this domain: prompt engineering and fine-tuning. Prompt engineering involves…

Context: The rapid evolution of Large Language Models (LLMs) has sparked significant interest in leveraging their capabilities for automating code review processes. Prior studies often focus on developing LLMs for code review automation,…

Multi-Criteria Decision Making~(MCDM) is widely applied in various fields, using quantitative and qualitative analyses of multiple levels and attributes to support decision makers in making scientific and rational decisions in complex…

The integration of large language models (LLMs) into automated algorithm design has shown promising potential. A prevalent approach embeds LLMs within search routines to iteratively generate and refine candidate algorithms. However, most…

Despite the massive success of fine-tuning Pre-trained Language Models (PLMs), they remain susceptible to out-of-distribution input. Dataset cartography is a simple yet effective dual-model approach that improves the robustness of…

Code review is a critical practice in modern software engineering, helping developers detect defects early, improve code quality, and facilitate knowledge sharing. With the rapid advancement of large language models (LLMs), a growing body…

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…

With the burgeoning development in the realm of large language models (LLMs), the demand for efficient incremental training tailored to specific industries and domains continues to increase. Currently, the predominantly employed frameworks…

Recently, researchers have proposed many multi-agent frameworks for function-level code generation, which aim to improve software development productivity by automatically generating function-level source code based on task descriptions. A…

Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a…

Code data in large language model (LLM) pretraining is recognized crucial not only for code-related tasks but also for enhancing general intelligence of LLMs. Current open-source LLMs often heavily rely on human effort to produce their code…

Multimodal Large Language Models (MLLMs) have made significant advancements, demonstrating powerful capabilities in processing and understanding multimodal data. Fine-tuning MLLMs with Federated Learning (FL) allows for expanding the…

The emergence of Multi-modal Large Language Models (MLLMs) presents new opportunities for chart understanding. However, due to the fine-grained nature of these tasks, applying MLLMs typically requires large, high-quality datasets for…

Reinforcement learning (RL) with verifiable rewards has proven effective at post-training LLMs for coding, yet deploying separate task-specific specialists incurs costs that scale with the number of tasks, motivating a unified multi-task RL…

Recent advancements in Large Language Models (LLMs) have emphasized the critical role of fine-tuning (FT) techniques in adapting LLMs to specific tasks, especially when retraining from scratch is computationally infeasible. Fine-tuning…

Many applications today use large language models for code generation; however, production systems have strict latency requirements that can be difficult to meet with large models. Small language models with a few billion parameters are…

Transformer-based, pre-trained large language models (LLMs) have demonstrated outstanding performance across diverse domains, particularly in the emerging {\em pretrain-then-finetune} paradigm. Low-Rank Adaptation (LoRA), a…

Code completion is one of the most useful features in the Integrated Development Environments (IDEs), which can accelerate software development by suggesting the next probable token based on the contextual code in real-time. Recent studies…