12 papers
Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
Yaorui Shi, Yuxin Chen, Siyuan Wang +5
Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large langu…
SAFER: Probing Safety in Reward Models with Sparse Autoencoder
Wei Shi, Ziyuan Xie, Sihang Li +1
Reinforcement learning from human feedback (RLHF) is a key paradigm for aligning large language models (LLMs) with human values, yet the reward models at its core remain largely op…
Interpretable Reward Model via Sparse Autoencoder
Shuyi Zhang, Wei Shi, Sihang Li +3
Large language models (LLMs) have been widely deployed across numerous fields. Reinforcement Learning from Human Feedback (RLHF) leverages reward models (RMs) as proxies for human…
Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling
Yanchen Luo, Zhiyuan Liu, Yi Zhao +6
3D molecule generation is crucial for drug discovery and material science, requiring models to process complex multi-modalities, including atom types, chemical bonds, and 3D coordi…
Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
Yaorui Shi, Sihang Li, Chang Wu +5
Large language models have demonstrated impressive reasoning capabilities but are inherently limited by their knowledge reservoir. Retrieval-augmented reasoning mitigates this limi…
Route Sparse Autoencoder to Interpret Large Language Models
Wei Shi, Sihang Li, Tao Liang +4
Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demons…