4 papers
Hidden Consensus:Preference-Validity Compression in Human Feedback
Dorcas Chia Ern Chua, Karen Myn Hui Lee, Jia Yue Tan +9
Standard RLHF pipelines often reduce heterogeneous human judgments into a single scalar reward target. We argue that this reduction can mis-measure alignment in structurally plural…
They Are Not the Same: Direct Causes Are Not Grounded Emotion Explanations
Zhuangzhuang Pan, Yan Xia, Chee Seng Chan
Emotion-Cause Pair Extraction (ECPE) was introduced to explain why an emotion occurs, but this goal is now often reduced to binary pair/non-pair prediction. This proxy is useful fo…
Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis
Yan Xia, Zhuangzhuang Pan, Amirrudin Kamsin +1
Aspect-Term Sentiment Analysis (ATSA) in multi-aspect sentences faces a fundamental tradeoff between efficiency and expressiveness. Existing models either re-encode the sentence fo…
VISTA: A Visual and Textual Attention Dataset for Interpreting Multimodal Models
Harshit, Tolga Tasdizen
The recent developments in deep learning led to the integration of natural language processing (NLP) with computer vision, resulting in powerful integrated Vision and Language Mode…