Behavioral Forgetting Is Not Privacy in Machine Unlearning

Summary

This research argues that behavioral forgetting, measured only on a designated benchmark distribution, is an insufficient standard for privacy-oriented machine unlearning in large language models. In a controlled case study of cross-lingual querying across multiple multilingual model families, forgetting varied substantially when semantically equivalent information was queried in different languages and scripts. The authors conclude that a single access path can expose a real gap between behavioral forgetting and information inaccessibility.

Topics

• Training data and privacy