Researchers have developed OPTI-Q, a new framework designed to optimize question planning for multiple large language models (LLMs). This system uses a database-inspired, cost-based optimizer to create execution plans that balance answer quality with resource constraints like cost, latency, and energy. OPTI-Q models LLM calls as operators in a directed acyclic graph and searches for optimal plans by estimating the quality and resource usage of different operator combinations using a performance database. Experiments on MMLU-Pro and SimpleQA benchmarks showed OPTI-Q significantly improved average answer quality compared to baseline methods while staying within specified budgets. AI
IMPACT This framework could enable more efficient and cost-effective deployment of LLM-based question-answering systems.
RANK_REASON The cluster contains an academic paper detailing a new framework for LLM question planning. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
