Unlocking LLM Creativity in Science through Analogical Reasoning

TL;DR

This paper introduces analogical reasoning (AR) to enhance the diversity and novelty of solutions generated by large language models in scientific discovery, especially in biomedicine.

Contribution

The paper proposes AR as a new method to improve solution diversity and novelty in LLMs, validated across multiple biomedical tasks with significant performance gains.

Findings

AR increases solution diversity by 90-173%.

AR generates solutions over 50% of the time, outperforming baselines.

AR achieves state-of-the-art results in biomedical prediction tasks.

Abstract

Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that can consistently generate novel and diverse solutions to open-ended problems. We evaluate LLMs on the task of open-ended solution generation and quantify their tendency to mode collapse into low-diversity generations. To mitigate this mode collapse, we introduce analogical reasoning (AR) as a new approach to solution generation. AR generates analogies to cross-domain problems based on shared relational structure, then uses those analogies to search for novel solutions. Compared to baselines, AR discovers significantly more diverse generations (improving solution diversity metrics by 90-173%), generates novel solutions over 50% of the time (compared to as little as 1.6% for baselines), and produces high-quality analogies. To validate the real-world feasibility of AR, we implement AR-generated solutions across four biomedical problems, yielding consistent quantitative gains. AR-generated approaches achieve a nearly 13-fold improvement on distributional metrics for perturbation effect prediction, outperform all baselines on AUPRC when predicting cell-cell communication, infer brain region interactions with a high Spearman correlation ($\rho$=0.729) to published methods, and establish state-of-the-art performance on 2 datasets for oligonucleotide property prediction. The novel and diverse solutions produced by AR can be used to augment the search space of existing solution generation methods.