5 papers
Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts
Jingting Zheng, Yuqi Ren, Linhao Yu +2
Large Language Models (LLMs) are increasingly deployed in contexts requiring complex moral reasoning and value trade-offs. However, existing evaluations typically rely on item-leve…
DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision
Yongqi Leng, Yikun Lei, Xikai Liu +7
Agentic Retrieval-Augmented Generation (Agentic RAG) enhances the processing capability for complex tasks through dynamic retrieval and adaptive workflows. Recent advances (e.g., S…
Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons
Yongqi Leng, Deyi Xiong
While large language models (LLMs) have demonstrated superior multi-task capabilities, understanding the learning mechanisms behind this is still a challenging problem. In this pap…
Large Language Model Safety: A Holistic Survey
Dan Shi, Tianhao Shen, Yufei Huang +10
The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural lang…
Self-Pluralising Culture Alignment for Large Language Models
Shaoyang Xu, Yongqi Leng, Linhao Yu +1
As large language models (LLMs) become increasingly accessible in many countries, it is essential to align them to serve pluralistic human values across cultures. However, pluralis…