Papers by Yuanqi Yao
Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to watermark low-entropy content are expensive and risky . IE reduces parameter size by 99% while achieving performance on par with state-of-the-art methods . |
| Approach: | They propose a logit-based watermarking paradigm that uses entropy-based features to predict whether the next token is high or low. |
| Outcome: | The proposed method reduces parameter size by 99% while achieving performance on par with state-of-the-art methods. |
From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to unlearning often treat nonsensical responses or template-based refusals as the unlearning target, making the process even more vulnerable to attacks and jailbreaks. |
| Approach: | They propose a method that uses inverted facts to remove the need for auxiliary models or retaining data while avoiding leakage. |
| Outcome: | Evaluated on the ToFU Knowledge Unlearning dataset using Llama2-7B-Chat and Phi-1.5, MEOW outperforms baselines in forgetting quality while preserving model utility. |