7 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…
Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information
Xu Chu, Xinrong Chen, Guanyu Wang +5
Inference time scaling drives extended reasoning to enhance the performance of Vision-Language Models (VLMs), thus forming powerful Vision-Language Reasoning Models (VLRMs). Howeve…
Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains
Xu Chu, Zhijie Tan, Hanlin Xue +3
Large Language Models (LLMs) are widely applied to downstream domains. However, current LLMs for high-stakes domain tasks, such as financial investment and legal QA, typically gene…
GraphSOS: Graph Sampling and Order Selection to Help LLMs Understand Graphs Better
Xu Chu, Hanlin Xue, Zhijie Tan +3
The success of Large Language Models (LLMs) in various domains has led researchers to apply them to graph-related problems by converting graph data into natural language text. Howe…
Mitigating Hallucinations on Object Attributes using Multiview Images and Negative Instructions
Zhijie Tan, Yuzhi Li, Shengwei Meng +5
Current popular Large Vision-Language Models (LVLMs) are suffering from Hallucinations on Object Attributes (HoOA), leading to incorrect determination of fine-grained attributes in…
Adaptive Spatiotemporal Augmentation for Improving Dynamic Graph Learning
Xu Chu, Hanlin Xue, Bingce Wang +5
Dynamic graph augmentation is used to improve the performance of dynamic GNNs. Most methods assume temporal locality, meaning that recent edges are more influential than earlier ed…