Get the latest tech news
Alibaba's ZeroSearch Teaches AI To Search Without Search Engines, Cuts Training Costs By 88%
Alibaba Group researchers have developed "ZeroSearch," a technique that enables large language models to acquire search capabilities without using external search engines during training. The approach transforms LLMs into retrieval modules through supervised fine-tuning and employs a "curriculum-bas...
The approach transforms LLMs into retrieval modules through supervised fine-tuning and employs a "curriculum-based rollout strategy" that gradually degrades generated document quality.In tests across seven question-answering datasets, ZeroSearch matched or exceeded the performance[PDF] of models trained with real search engines. A 7B-parameter retrieval module achieved results comparable to Google Search, while a 14B-parameter version outperformed it. Researchers have released their code, datasets, and pre-trained models on GitHub and Hugging Face, potentially lowering barriers to entry for smaller AI companies developing sophisticated assistants.
Or read this on Slashdot
