幻覺在藥物發現中有助於提升大型語言模型

Hallucinations Can Improve Large Language Models in Drug Discovery

January 23, 2025

作者: Shuzhou Yuan, Michael Färber

cs.AI

摘要

研究人員提出了關於大型語言模型（LLMs）中幻覺的擔憂，然而在創造力至關重要的領域，如藥物發現，它們的潛力值得探索。本文提出了一個假設，即幻覺可以改善LLMs在藥物發現中的應用。為驗證這一假設，我們使用LLMs將分子的SMILES字符串用自然語言描述，然後將這些描述作為提示的一部分，以應對藥物發現中的特定任務。在七個LLMs和五個分類任務上進行評估後，我們的研究結果證實了這一假設：LLMs在包含幻覺文本時可以實現更好的性能。值得注意的是，Llama-3.1-8B相比沒有幻覺的基準線，ROC-AUC增益達到18.35％。此外，由GPT-4o生成的幻覺在各模型中提供了最一致的改進。此外，我們進行了實證分析和案例研究，以探討影響性能和潛在原因的關鍵因素。我們的研究為LLMs利用幻覺的潛在應用提供了新的視角，並為未來在藥物發現中利用LLMs的研究提供了新的觀點。

English

Concerns about hallucinations in Large Language Models (LLMs) have been raised by researchers, yet their potential in areas where creativity is vital, such as drug discovery, merits exploration. In this paper, we come up with the hypothesis that hallucinations can improve LLMs in drug discovery. To verify this hypothesis, we use LLMs to describe the SMILES string of molecules in natural language and then incorporate these descriptions as part of the prompt to address specific tasks in drug discovery. Evaluated on seven LLMs and five classification tasks, our findings confirm the hypothesis: LLMs can achieve better performance with text containing hallucinations. Notably, Llama-3.1-8B achieves an 18.35% gain in ROC-AUC compared to the baseline without hallucination. Furthermore, hallucinations generated by GPT-4o provide the most consistent improvements across models. Additionally, we conduct empirical analyses and a case study to investigate key factors affecting performance and the underlying reasons. Our research sheds light on the potential use of hallucinations for LLMs and offers new perspectives for future research leveraging LLMs in drug discovery.