Role-RL: Online Long-Context Processing with Role Reinforcement Learning for Distinct LLMs in Their Optimal Roles
This addresses the problem of efficient and cost-effective long-context processing for applications like automated news reporting and live e-commerce, representing a novel approach rather than an incremental improvement.
The paper tackles the challenge of processing unlimited-length documents in streaming media by proposing an Online Long-context Processing (OLP) paradigm and Role Reinforcement Learning (Role-RL) to automatically deploy LLMs in optimal roles, achieving an average recall rate of 93.2% and saving LLM costs by 79.4%.
Large language models (LLMs) with long-context processing are still challenging because of their implementation complexity, training efficiency and data sparsity. To address this issue, a new paradigm named Online Long-context Processing (OLP) is proposed when we process a document of unlimited length, which typically occurs in the information reception and organization of diverse streaming media such as automated news reporting, live e-commerce, and viral short videos. Moreover, a dilemma was often encountered when we tried to select the most suitable LLM from a large number of LLMs amidst explosive growth aiming for outstanding performance, affordable prices, and short response delays. In view of this, we also develop Role Reinforcement Learning (Role-RL) to automatically deploy different LLMs in their respective roles within the OLP pipeline according to their actual performance. Extensive experiments are conducted on our OLP-MINI dataset and it is found that OLP with Role-RL framework achieves OLP benchmark with an average recall rate of 93.2% and the LLM cost saved by 79.4%. The code and dataset are publicly available at: https://anonymous.4open.science/r/Role-RL.