4 papers · 1 filter
HART: Data-Driven Hallucination Attribution and Evidence-Based Tracing for Large Language Models
Shize Liang, Hongzhi Wang
Large language models (LLMs) have demonstrated remarkable performance in text generation and knowledge-intensive question answering. Nevertheless, they are prone to producing hallu…
Explainable Multimodal Aspect-Based Sentiment Analysis with Dependency-guided Large Language Model
Zhongzheng Wang, Yuanhe Tian, Hongzhi Wang +1
Multimodal aspect-based sentiment analysis (MABSA) aims to identify aspect-level sentiments by jointly modeling textual and visual information, which is essential for fine-grained…
Neural Probe-Based Hallucination Detection for Large Language Models
Shize Liang, Hongzhi Wang
Large language models(LLMs) excel at text generation and knowledge question-answering tasks, but they are prone to generating hallucinated content, severely limiting their applicat…
Self-Regulated Data-Free Knowledge Amalgamation for Text Classification
Prashanth Vijayaraghavan, Hongzhi Wang, Luyao Shi +3
Recently, there has been a growing availability of pre-trained text models on various model repositories. These models greatly reduce the cost of training new models from scratch a…