Alibaba's ZeroSearch Teaches AI To Search Without Search Engines, Cuts Training Costs By 88%

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-based rollout strategy" that gradually degrades generated document quality. In tests across seven question-answering datasets, ZeroSearch matched or ex…

Alibaba ZeroSearch Cuts AI Training Costs by 88%

Alibaba Develops ZeroSearch To Cut AI Costs Researchers engineered a simulation method to replace commercial search engines in model training. This innovation reduces expenses by 88% and increases control over… The post Alibaba ZeroSearch Cuts AI Training Costs by 88% appeared first on nextbigwhat.

Alibaba researchers detail ZeroSearch, a technique allowing LLMs to develop advanced search capabilities via simulation, claiming it cuts costs by up to 88%

Top news and commentary for technology's leaders, from all around the web.

Alibaba’s ZeroSearch Enhances AI Search Efficiency

Alibaba has introduced ZeroSearch, an innovative reinforcement learning framework designed to enhance the search capabilities of large models without directly interacting with real search engines. This framework leverages the extensive knowledge these models gather during large-scale pre-training to transform it into a retrieval module that can generate relevant content based on search queries. A unique feature of ZeroSearch is its ability to dy…