Branch-Solve-Merge Improves Large Language Model Evaluation and Generation

Understand

Large Language Models (LLMs) are frequently used for multi-faceted language generation and evaluation tasks that involve satisfying intricate user constraints or taking into account multiple aspects and criteria.

• However, their performance can fall short, due to the model's lack of coherence and inability to plan and decompose the problem.
• We propose Branch-Solve-Merge (BSM), a Large Language Model program (Schlag et al., 2023) for tackling such challenging natural language tasks.
• It consists of branch, solve, and merge modules that are parameterized with specific prompts to the base LLM.