Author

Liwei Jiang

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Safety Mid-Training: Internalizing LLM Safety as a Foundational Capability

Safety alignment for large language models (LLMs) is primarily performed during post-training, while recent work has also begun incorporating safety data into pre-training. Yet safety can degrade when later training no longer includes safety data, and gains in safety often come at the cost of general capability. This t...

Zheng-Yue Zhao, Li-Wei Jiang, Ye-Jin Choi et al. · 0 citations

#artificial intelligence Apr 2026

Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations

CarryOnBench is introduced, the first interactive benchmark that measures whether LLMs can revise their interpretation of user intent and recover utility, while remaining safe through multi-turn conversations, and Ben-Util, a checklist-based metric that evaluates how well each model response fulfills the user's benign...

Ming-Qian Zheng, Malia Morgan, Liwei Jiang et al. · arXiv.org · 3 citations · ⚡1