alphaXiv

Explore

State of the Art

Sign In

Labs

Feedback

Browser Extension

We're hiring
PaperBlogResources

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

BibTex
Copy
@misc{zhou2025mixdatamerge,
      title={Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and  Harmlessness of Large Language Model via Model Merging}, 
      author={Jun Zhou and Li Shen and Kun Kuang and Fei Wu and Zhengyu Chen and Qing Cui and Zhiqiang Zhang and Anke Tang and Jinluan Yang and Didi Zhu and Daixin Wang and Dingnan Jin},
      year={2025},
      eprint={2502.06876},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2502.06876}, 
}
Transform this paper into an audio lecture
Get an engaging lecture and Q&A format to quickly understand the paper in minutes, perfect for learning on the go.
Audio lecture
Q&A format