5 papers
Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations
Li Zhou, Hao Jiang, Junjie Li +4
Explicit structural information has been proven to be encoded by Graph Neural Networks (GNNs), serving as auxiliary knowledge to enhance model capabilities and improve performance…
QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
Wanlong Liu, Junxiao Xu, Fei Yu +7
Recent advancements in Long Chain-of-Thought (CoT) reasoning models have improved performance on complex tasks, but they suffer from overthinking, which generates redundant reasoni…
Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge
Li Zhou, Taelin Karidi, Wanlong Liu +5
Recent studies have highlighted the presence of cultural biases in Large Language Models (LLMs), yet often lack a robust methodology to dissect these phenomena comprehensively. Our…
Mixed-Precision Graph Neural Quantization for Low Bit Large Language Models
Wanlong Liu, Yichen Xiao, Dingyi Zeng +3
Post-Training Quantization (PTQ) is pivotal for deploying large language models (LLMs) within resource-limited settings by significantly reducing resource demands. However, existin…
RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions
Wanlong Liu, Junying Chen, Ke Ji +3
Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models (LLMs) by incorporating external knowledge. However, current RAG methods face…