5 papers
Better Datasets Start From RefineLab: Automatic Optimization for High-Quality Dataset Refinement
Xiaonan Luo, Yue Huang, Ping He +1
High-quality Question-Answer (QA) datasets are foundational for reliable Large Language Model (LLM) evaluation, yet even expert-crafted datasets exhibit persistent gaps in domain c…
SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization
Yue Huang, Xiangqi Wang, Xiangliang Zhang
In high-stakes scenarios-such as self-harm, legal, or medical queries-LLMs must be both trustworthy and helpful. However, these goals often conflict. We propose priority alignment,…
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models
Lang Gao, Jiahui Geng, Xiangliang Zhang +2
Jailbreaking in Large Language Models (LLMs) is a major security concern as it can deceive LLMs to generate harmful text. Yet, there is still insufficient understanding of how jail…
Evaluating and Mitigating Bias in AI-Based Medical Text Generation
Xiuying Chen, Tairan Wang, Juexiao Zhou +3
Artificial intelligence (AI) systems, particularly those based on deep learning models, have increasingly achieved expert-level performance in medical applications. However, there…
Write Summary Step-by-Step: A Pilot Study of Stepwise Summarization
Xiuying Chen, Shen Gao, Mingzhe Li +3
Nowadays, neural text generation has made tremendous progress in abstractive summarization tasks. However, most of the existing summarization models take in the whole document all…