7 papers
HindSearch: Trajectory-Level Hindsight Critique for Search-Augmented Reinforcement Learning
Haowei Liu, Jiamian Wang, Hsin-Tai Wu +2
Search-augmented LM agents are typically trained with a binary exact-match reward, which throws away most of what a failed trajectory tells us about why it failed. We introduce Hin…
Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts
Xuyang Wu, Yuan Wang, Hsin-Tai Wu +2
Large vision-language models (LVLMs) have recently achieved significant progress, demonstrating strong capabilities in open-world visual understanding. However, it is not yet clear…
RaCT: Ranking-aware Chain-of-Thought Optimization for LLMs
Haowei Liu, Xuyang Wu, Guohao Sun +2
In information retrieval, large language models (LLMs) have demonstrated remarkable potential in text reranking tasks by leveraging their sophisticated natural language understandi…
Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems
Xuyang Wu, Shuowei Li, Hsin-Tai Wu +2
Retrieval-Augmented Generation (RAG) has recently gained significant attention for its enhanced ability to integrate external knowledge sources into open-domain question answering…
CLERF: Contrastive LEaRning for Full Range Head Pose Estimation
Ting-Ruen Wei, Haowei Liu, Huei-Chung Hu +3
We introduce a novel framework for representation learning in head pose estimation (HPE). Previously such a scheme was difficult due to head pose data sparsity, making triplet samp…
Table Transformers for Imputing Textual Attributes
Ting-Ruen Wei, Yuan Wang, Yoshitaka Inoue +2
Missing data in tabular dataset is a common issue as the performance of downstream tasks usually depends on the completeness of the training dataset. Previous missing data imputati…