Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solving
Primary Area: neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Large Language Models, Reasoning, Hierarchical Policy
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Abstract: Large Language Models (LLMs) have achieved tremendous progress, yet they still often struggle with challenging reasoning problems. Current approaches address this challenge by sampling or searching detailed and low-level reasoning chains. However, these methods are still limited in their exploration capabilities, making it challenging for correct solutions to stand out in the huge solution space. In this work, we unleash LLMs' creative potential for exploring multiple diverse problem solving strategies by framing an LLM as a hierarchical policy via in-context learning. This policy comprises of a visionary leader that proposes multiple diverse high-level problem-solving tactics as hints, accompanied by a follower that executes detailed problem-solving processes following each of the high-level instruction. The follower uses each of the leader's directives as a guide and samples multiple reasoning chains to tackle the problem, generating a solution group for each leader proposal. Additionally, we propose an effective and efficient tournament-based approach to select among these explored solution groups to reach the final answer. Our approach produces meaningful and inspiring hints, enhances problem-solving strategy exploration, and improves the final answer accuracy on challenging problems in the MATH dataset.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 453
Loading