Papers by Xingjun Zhang
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for defending NLP models against backdoors have ignored the clean weights of PLMs. |
| Approach: | They exploit pre-trained weights to mitigate backdoors in fine-tuned NLP models . they use a fine-mixing technique and an Embedding Purification technique to do the same . |
| Outcome: | The proposed method outperforms baseline mitigation methods on three single-sentence sentiment classification tasks and two sentence-pair classification tasks. |
Fake Alignment: Are LLMs Really Aligned Well? (2024.naacl-long)
Copied to clipboard
Yixu Wang, Yan Teng, Kexin Huang, Chengqi Lyu, Songyang Zhang, Wenwei Zhang, Xingjun Ma, Yu-Gang Jiang, Yu Qiao, Yingchun Wang
| Challenge: | Existing studies on large language models have shown that they are poorly aligned in practice. |
| Approach: | They propose a framework to evaluate safety in large language models . they propose two new metrics to quantify fake alignment and obtain corrected performance estimation. |
| Outcome: | The proposed framework and two metrics show that some models with purported safety are poorly aligned in practice. |
WRP: Weight Recover Prune for Structured Sparsity (2024.acl-long)
Copied to clipboard
| Challenge: | Existing pruning and quantization algorithms could compress LLMs to 4 bits without retraining. |
| Approach: | They propose a method to prune models using a minimal set of critical weights . they compare the method to a 2:4 structured sparsity method . |
| Outcome: | The proposed method outperforms other methods on LLAMA2 and OPT models while maintaining the efficiency of the compression. |