OLAPH: Improving Factuality in Biomedical Long-form Question Answering
Keywords: medical question answering, automatic evaluation, factuality, hallucination
Abstract: In the medical domain, numerous scenarios necessitate the long-form generation ability of large language models (LLMs). Specifically, when addressing patients' questions, it is essential that the model's response conveys factual claims, highlighting the need for an automated method to evaluate those claims. Thus, we introduce MedLFQA, a benchmark dataset reconstructed using long-form question-answering datasets related to the biomedical domain. We use MedLFQA to facilitate a cost-effective automatic evaluations of factuality. We also propose OLAPH, a simple and novel framework that utilizes cost-effective and multifaceted automatic evaluation to construct a synthetic preference set and answers questions in our preferred manner. Our framework leads us to train LLMs step-by-step to reduce hallucinations and include crucial medical claims. We highlight that, even on evaluation metrics not used during training, LLMs trained with our OLAPH framework demonstrate significant performance improvement in factuality. Our findings reveal that a 7B LLM trained with our OLAPH framework can provide long answers comparable to the medical experts' answers in terms of factuality. We believe that our work could shed light on gauging the long-text generation ability of LLMs in the medical domain. Our code and datasets are available.
Primary Area: applications to physical sciences (physics, chemistry, biology, 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.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
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: 6118
Loading