4 papers
Towards Automated Kernel Generation in the Era of LLMs
Yang Yu, Peiyu Zang, Chi Hsu Tsai +11
The performance of modern AI systems is fundamentally constrained by the quality of their underlying GPU kernels, which translate high-level algorithmic semantics into low-level ha…
MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination
Ao Jia, Haiming Wu, Guohui Yao +3
Large language models (LLMs) are prone to three types of hallucination: Input-Conflicting, Context-Conflicting and Fact-Conflicting hallucinations. The purpose of this study is to…
Bi-DCSpell: A Bi-directional Detector-Corrector Interactive Framework for Chinese Spelling Check
Haiming Wu, Hanqing Zhang, Richeng Xuan +1
Chinese Spelling Check (CSC) aims to detect and correct potentially misspelled characters in Chinese sentences. Naturally, it involves the detection and correction subtasks, which…
Controllable Text Generation with Residual Memory Transformer
Hanqing Zhang, Sun Si, Haiming Wu +1
Large-scale Causal Language Models (CLMs), e.g., GPT3 and ChatGPT, have brought great success in text generation. However, it is still an open challenge to control the generation p…