8 papers
Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization
Xu Chu, Guanyu Wang, Zhijie Tan +4
Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness limits the model's applications…
Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
Xinrong Chen, Xu Chu, Yingmin Qiu +8
Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and…
Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity
Hengyuan Zhang, Xinrong Chen, Zunhai Su +10
Layer-wise mixed-precision quantization (LMPQ) enables effective compression under extreme low-bit settings by allocating higher precision to sensitive layers. However, existing me…
MORE-R1: Guiding LVLM for Multimodal Object-Entity Relation Extraction via Stepwise Reasoning with Reinforcement Learning
Xiang Yuan, Xu Chu, Xinrong Chen +6
Multimodal Object-Entity Relation Extraction (MORE) is a challenging task in information extraction research. It aims to identify relations between visual objects and textual entit…
Stepwise Schema-Guided Prompting Framework with Parameter Efficient Instruction Tuning for Multimedia Event Extraction
Xiang Yuan, Xinrong Chen, Haochen Li +4
Multimedia Event Extraction (MEE) has become an important task in information extraction research as news today increasingly prefers to contain multimedia content. Current MEE work…
GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors
Hengyuan Zhang, Xinrong Chen, Yingmin Qiu +7
Parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), offer an efficient way to adapt large language models with reduced computational costs. How…