Search Results for author: Jiamin Luo

Found 3 papers, 0 papers with code

ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues

no code implementations8 Mar 2024 Yiding Liu, Jingjing Wang, Jiamin Luo, Tao Zeng, Guodong Zhou

Specifically, this TSA treats the ACR task as an auxiliary task to boost the performance of the primary ASU task, and further integrates trusted learning into reflexion mechanisms to alleviate the LLMs-intrinsic factual hallucination problem in TSA.

Hallucination Question Answering

TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection

no code implementations4 Mar 2024 Jiamin Luo, Jingjing Wang, Guodong Zhou

Multimodal Conversational Emotion (MCE) detection, generally spanning across the acoustic, vision and language modalities, has attracted increasing interest in the multimedia community.

How to Understand "Support"? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding

no code implementations29 Feb 2024 Jiamin Luo, Jianing Zhao, Jingjing Wang, Guodong Zhou

Weakly-supervised Phrase Grounding (WPG) is an emerging task of inferring the fine-grained phrase-region matching, while merely leveraging the coarse-grained sentence-image pairs for training.

Causal Inference counterfactual +3

Cannot find the paper you are looking for? You can Submit a new open access paper.