5 papers
What to Preserve in Recursive Computation: A Local Predictive Sufficiency Principle
Peilin Wang, Feng Shiyang, Hongfu Gao +4
Recursive computation repeatedly compresses or reuses intermediate states, creating a simple tension: information that must remain useful across longer recursive paths is also expo…
Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes
Hongfu Gao, Songxin Zhang, Zejian Xie +3
Large language model (LLM) leaderboards compare model capabilities by ranking models according to their mean performance on fixed benchmarks. However, variability in evaluation out…
Exploring Imbalanced Annotations for Effective In-Context Learning
Hongfu Gao, Feipeng Zhang, Hao Zeng +3
Large language models (LLMs) have shown impressive performance on downstream tasks through in-context learning (ICL), which heavily relies on the demonstrations selected from annot…
ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models
Hengxiang Zhang, Hongfu Gao, Qiang Hu +7
With the rapid development of Large language models (LLMs), understanding the capabilities of LLMs in identifying unsafe content has become increasingly important. While previous w…
On the Noise Robustness of In-Context Learning for Text Generation
Hongfu Gao, Feipeng Zhang, Wenyu Jiang +3
Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from…