← authors · overview

• Anyedit: Edit Any Knowledge Encoded In Language Models
  2025 · 62 citations
• Attack Prompt Generation for Red Teaming and Defending Large Language Models
  2023 · 28 citations
• Large Language Model Can Interpret Latent Space of Sequential Recommender
  2023 · 6 citations
• $e̱ta$-DPO: Direct Preference Optimization with Dynamic $e̱ta$
  2024 · 5 citations
• Less is More: Improving LLM Alignment via Preference Data Selection
  2025 · 2 citations
• Item-side Fairness of Large Language Model-based Recommendation System
  2024 · 2 citations
• Preliminary Study on Incremental Learning for Large Language Model-based Recommender Systems
  2023 · 1 citations
• Text-like Encoding of Collaborative Information in Large Language Models for Recommendation
  2024 · 1 citations
• Contrastive Weak-to-strong Generalization
  2025
• DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulation
  2025
• Route Sparse Autoencoder to Interpret Large Language Models
  2025
• DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
  2025
• Exact and Efficient Unlearning for Large Language Model-based Recommendation
  2024
• Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
  2024
• Unified Parameter-Efficient Unlearning for LLMs
  2024