Can Hallucinations Help? Boosting LLMs for Drug Discovery
This work addresses the challenge of enhancing LLM performance in scientific modeling tasks like drug discovery, offering a novel approach by leveraging hallucinations, though it is incremental as it builds on existing methods for a specific domain.
The paper tackled the problem of improving LLMs for molecule property prediction in drug discovery by incorporating hallucinated text, finding that hallucinations significantly boosted predictive accuracy for some models, with Falcon3-Mamba-7B outperforming baselines and GPT-4o hallucinations yielding the greatest gains.
Hallucinations in large language models (LLMs), plausible but factually inaccurate text, are often viewed as undesirable. However, recent work suggests that such outputs may hold creative potential. In this paper, we investigate whether hallucinations can improve LLMs on molecule property prediction, a key task in early-stage drug discovery. We prompt LLMs to generate natural language descriptions from molecular SMILES strings and incorporate these often hallucinated descriptions into downstream classification tasks. Evaluating seven instruction-tuned LLMs across five datasets, we find that hallucinations significantly improve predictive accuracy for some models. Notably, Falcon3-Mamba-7B outperforms all baselines when hallucinated text is included, while hallucinations generated by GPT-4o consistently yield the greatest gains between models. We further identify and categorize over 18,000 beneficial hallucinations, with structural misdescriptions emerging as the most impactful type, suggesting that hallucinated statements about molecular structure may increase model confidence. Ablation studies show that larger models benefit more from hallucinations, while temperature has a limited effect. Our findings challenge conventional views of hallucination as purely problematic and suggest new directions for leveraging hallucinations as a useful signal in scientific modeling tasks like drug discovery.