Rethinking Text-based Protein Understanding: Retrieval or LLM?

ACL ARR 2025 May Submission114 Authors

Abstract: In recent years, protein-text models have gained significant attention for their potential in protein generation and understanding. Current approaches focus on integrating protein-related knowledge into large language models through continued pretraining and multi-modal alignment, enabling simultaneous comprehension of textual descriptions and protein sequences. Through a thorough analysis of existing model architectures and text-based protein understanding benchmarks, we identify significant data leakage issues present in current benchmarks. Moreover, conventional metrics derived from natural language processing fail to accurately assess the model's performance in this domain. To address these limitations, we reorganize existing datasets and introduce a novel evaluation framework based on biological entities. Motivated by our observation, we propose a retrieval-enhanced method, which significantly outperforms fine-tuned LLMs for protein-to-text generation and shows accuracy and efficiency in training-free scenarios. Our code and data will be available.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: Protein Language model; Retrieval Augmented Generation; Protein Understanding

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources, Data analysis

Languages Studied: English

Keywords: Protein Language model; Retrieval Augmented Generation; Protein Understanding

Submission Number: 114