4 papers
ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders
Xiangyu Liu, Haodi Lei, Yi Liu +2
Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming…
Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition
Yi Liu, Xiangrong Zhu, Xiangyu Liu +2
In a rapidly evolving world where information updates swiftly, knowledge in large language models (LLMs) becomes outdated quickly. Retraining LLMs is not a cost-effective option, m…
Knowledge Graph-Guided Retrieval Augmented Generation
Xiangrong Zhu, Yuexiang Xie, Yi Liu +2
Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing…
Controllable Protein Sequence Generation with LLM Preference Optimization
Xiangyu Liu, Yi Liu, Silei Chen +1
Designing proteins with specific attributes offers an important solution to address biomedical challenges. Pre-trained protein large language models (LLMs) have shown promising res…