Programming languages possess rich semantic information - such as data flow - that is represented by graphs and not available from the surface form of source code. Recent code language models have scaled to billions of parameters, but model source code solely as text tokens while ignoring any other structural information. Conversely, models that do encode structural information of code make modifications to the Transformer architecture, limiting their scale and compatibility with pretrained LLMs. In this work, we take the best of both worlds with GALLa - Graph Aligned Large Language Models. GALLa utilizes graph neural networks and cross-modal alignment technologies to inject the structural information of code into LLMs as an auxiliary task during finetuning. This framework is both model-agnostic and task-agnostic, as it can be applied to any code LLM for any code downstream task, and requires the structural graph data only at training time from a corpus unrelated to the finetuning data, while incurring no cost at inference time over the baseline LLM. Experiments on five code tasks with seven different baseline LLMs ranging in size from 350M to 14B validate the effectiveness of GALLa, demonstrating consistent improvement over the baseline, even for powerful models such as LLaMA3 and Qwen2.5-Coder.
Optimizing Diversity and Quality through Base-Aligned Model Collaboration
University of Chicago(芝加哥大学);University of Southern California, Information Sciences Institute(南加州大学信息科学研究所);University of California, Davis(加州大学戴维斯分校)
QQJ: Quantifying Qualitative Judgment for Scalable and Human-Aligned Evaluation of Generative AI
AI Lab, Arioobarzan Engineering Team(艾伊罗巴赞工程团队人工智能实验室);Department of Computer Engineering and Information Technology(计算机工程与信息科技系);Department of Informatics, Bioengineering, Robotics and Systems Engineering(信息学、生物工程、机器人与系统工程系);University of Genoa(热那亚大学)
GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning
Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University(交叉信息学院(IIIS)、清华大学);Language Technologies Institute (LTI), Carnegie Mellon University(语言技术研究所(LTI)、卡内基梅隆大学)
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Alibaba Group(阿里巴巴集团);Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen)(广东人工智能与数字经济实验室(深圳))