Papers by Naixin Zhai
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to machine unlearning treat all tokens indiscriminately and enforce uncertainty over the entire vocabulary. |
| Approach: | They propose a framework that targets the prefix in a response and minimizes uncertainty in the critical subspace. |
| Outcome: | The proposed framework achieves superior forgetting efficacy and utility preservation compared to baselines. |