Papers by Ning Shang
Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work has shown that safety behaviors are governed by low-rank structures . Low-Rank Adaptation (LoRA) consistently underperforms full fine-tuning and reinforcement learning on safety benchmarks . |
| Approach: | They propose a safety alignment system that disentangles safety-relevant directions into monosemantic features and constructs an interpretable safety subspace from SAE directions. |
| Outcome: | Empirically, the proposed model achieves 99.6% safety rates across multiple model families and scales . low-rank Adaptation consistently underperforms full fine-tuning and reinforcement learning on safety benchmarks compared with previous methods . |
Towards Comprehensive Patent Approval Predictions:Beyond Traditional Document Classification (2022.acl-long)
Copied to clipboard
| Challenge: | a new framework for patent approval prediction is proposed to address this problem . novelty scores are based on comparing an application with millions of prior arts . |
| Approach: | They propose a framework that unifies the document classifier with handcrafted features, particularly time-dependent novelty scores. |
| Outcome: | The proposed framework unifies the document classifier with handcrafted features, particularly time-dependent novelty scores. |
Aligning to Constraints for Data-Efficient Language Model Customization (2025.findings-naacl)
Copied to clipboard
Fei Wang, Chao Shang, Shuai Wang, Sarthak Jain, Qiang Ning, Bonan Min, Vittorio Castelli, Yassine Benajiba, Dan Roth
| Challenge: | General-purpose language models (LMs) are aligned to diverse user intents, but fall short when it comes to specific applications. |
| Approach: | They propose a framework that uses constraints to automatically produce supervision signals for user alignment with constraints. |
| Outcome: | The proposed framework can produce supervision signals for user alignment with constraints. |
WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning (2024.acl-long)
Copied to clipboard
| Challenge: | Recent work shows that Code Large Language Models can address a wide range of code-related tasks. |
| Approach: | They propose a method to generate widespread and versatile instruction data from open source code datasets and use it to train code-related models. |
| Outcome: | The proposed model outperforms open-source models in generalization ability across code-related tasks. |