Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
This addresses the problem of biased reasoning in LLMs for researchers and practitioners in machine learning and chemistry, with incremental improvements on existing methods.
The paper tackles intrinsic biases in Large Language Models by introducing Flow-of-Options, a reasoning approach that systematically explores diverse possibilities, resulting in improvements of 38.2%-69.2% on data science tasks and 37.4%-47.9% on therapeutic chemistry tasks compared to state-of-the-art baselines.
We present a novel reasoning approach called Flow-of-Options (FoO), designed to address intrinsic biases in Large Language Models (LLMs). Flow-of-Options enables LLMs to systematically explore a diverse range of possibilities in their reasoning, as demonstrated by an FoO-based agentic framework developed for autonomously solving Machine Learning (ML) tasks. FoO enforces diversity in LLM solutions through compressed and interpretable task representations, resulting in improvements of 38.2% - 69.2% on standard data science tasks, and 37.4% - 47.9% on therapeutic chemistry tasks, as compared to state-of-the-art baselines. With an overall operation cost under $1 per task, our framework is well-suited for cost-sensitive applications. Going beyond tabular classification and regression, we show the broader applicability of our FoO-based agentic system to tasks such as reinforcement learning and image generation. Our code is open-sourced at: https://github.com/flagshippioneering/Flow-of-Options.