5 papers
Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules
Zhuocheng Gong, Ang Lv, Jian Guan +6
Is it always necessary to compute tokens from shallow to deep layers in Transformers? The continued success of vanilla Transformers and their variants suggests an undoubted "yes".…
Model Extrapolation Expedites Alignment
Chujie Zheng, Ziqi Wang, Heng Ji +2
Given the high computational cost of preference alignment training of large language models (LLMs), exploring efficient methods to reduce the training overhead remains an important…
AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback
Jian Guan, Wei Wu, Zujie Wen +3
The notable success of large language models (LLMs) has sparked an upsurge in building language agents to complete various complex tasks. We present AMOR, an agent framework based…
On Prompt-Driven Safeguarding for Large Language Models
Chujie Zheng, Fan Yin, Hao Zhou +5
Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) against queries with harmful intents. However, the underlying working…
Language Models Hallucinate, but May Excel at Fact Verification
Jian Guan, Jesse Dodge, David Wadden +2
Recent progress in natural language processing (NLP) owes much to remarkable advances in large language models (LLMs). Nevertheless, LLMs frequently "hallucinate," resulting in non…