Structured data, rich in logical and relational information, has the potential to enhance the reasoning abilities of large language models (LLMs). Still, its integration poses a challenge due to the risk of overwhelming LLMs with excessive tokens and irrelevant context information. To address this, we propose Struct-X, a novel framework that operates through five key phases: ``read-model-fill-reflect-reason'' efficiently enabling LLMs to utilize structured data. It begins by encoding structured data into a topological space using graph embeddings, followed by filling in missing entity information with knowledge retrieval modules, and filtering out irrelevant tokens via a self-supervised module. The final phase involves constructing a topological network with selected tokens to further reduce the total token length for more effective LLM inference. Additionally, Struct-X includes an Auxiliary Module trained to generate prompts, aiding LLMs in analyzing structured data. Extensive experiments on benchmarks, including the knowledge graph question-answer task and the long document reading comprehension task, show that Struct-X notably improves LLM reasoning, demonstrating the effectiveness of structured data augmentation in improving LLM inference with complex input context.
$\rm SP^3$: Enhancing Structured Pruning via PCA Projection
School of Information, Renmin University of China(中国人民大学信息学院);Tencent AI Lab, Tencent(腾讯AI实验室);School of Computer Science and Technology, Xi’an Jiaotong University(西安交通大学计算机科学与技术学院)
HYBRINFOX at CheckThat! 2024 -- Task 1: Enhancing Language Models with Structured Information for Check-Worthiness Estimation
Université de Rennes(雷恩大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);IRISA(雷恩信息、信号与自动化研究所);LIP6(巴黎第六大学信息学实验室);Sorbonne Université(索邦大学);Institut Jean-Nicod(让·尼科研究所);ENS-PSL(巴黎高等师范学院-PSL大学);EHESS(法国社会科学高等研究院)
本文提出用三元组结构化信息嵌入增强 RoBERTa 等语言模型,在 CheckThat! 2024 任务 1 英语可核查性估计中取得 F1 71.1、排名第 12,并展望将该流程适配到大语言模型。
Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation
Huzhou University(湖州大学);Zhejiang Key Laboratory of Intelligent Education Technology and Application(浙江智能教育技术与应用重点实验室);Banbu AI Foundation(Banbu AI基金会);Baichuan Inc(白川公司);University of Edinburgh(爱丁堡大学);Zhejiang University(浙江大学)
LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Models
Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University(复旦大学数据科学重点实验室,计算机科学与人工智能学院);School of Data Science, Fudan University(复旦大学数据科学学院);Ant Group(蚂蚁集团)
MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Framework
Center for Healthcare Organization and Implementation Research, VA Bedford Health Care(医疗组织与实施研究中心,VA贝德福德医疗中心);Miner School of Computer and Information Sciences, University of Massachusetts Lowell(矿物计算机与信息科学学院,马萨诸塞州立大学洛厄尔分校);Manning College of Information and Computer Sciences, University of Massachusetts Amherst(曼宁信息与计算机科学学院,马萨诸塞州立大学阿姆赫斯特分校)
Enhancing Multi-Hop Fact Verification with Structured Knowledge-Augmented Large Language Models
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
A Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated Tasks
DJCAD, University of Dundee, United Kingdom(邓迪大学DJCAD部门);ARG-tech, SSEN, University of Dundee, United Kingdom(邓迪大学);School of Computer Science, University of Birmingham, United Kingdom(伯明翰大学计算机科学学院)
Causal-aware Large Language Models: Enhancing Decision-Making Through Learning, Adapting and Acting
School of Computer Science, Guangdong University of Technology(广东技术大学计算机科学学院);College of Mathematics and Computer Science, Shantou University(汕头大学数学与计算机科学学院);Huawei Noah’s Ark Lab, Huawei(华为诺亚实验室);Peng Cheng Laboratory, Shenzhen, China(鹏城实验室)
DRS: Deep Question Reformulation With Structured Output
University of California, San Diego(加州大学圣地亚哥分校);University of California, Los Angelas(加州大学洛杉矶分校);The University of Queensland(昆士兰大学);National University of Singapore(新加坡国立大学)
TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning
Tsinghua University(清华大学);Nanyang Technological University(南洋理工大学);Princeton University(普林斯顿大学);Shanghai AI Lab(上海人工智能实验室);Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心)
VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
The Hong Kong University of Science and Technology(香港科学与技术大学);Nanyang Technological University(南洋理工大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insights
South China University of Technology(南方科技大学);HFIPS, Chinese Academy of Sciences(中国科学院HFIPS);University of Science and Technology of China(中国科学技术大学);The Third Affiliated Hospital of SuYat-sen University(孙逸德大学第三附属医院)
Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints
National Key Laboratory for Multimedia Information Processing, Peking University(北京大学多媒体信息处理国家重点实验室);School of Software and Microelectronics, Peking University(北京大学软件与微电子学院);Tsinghua University(清华大学)