Papers by Hiroki Furuta

1 papers
Understanding Emergent Misalignment via Feature Superposition Geometry (2026.acl-long)

Copied to clipboard

Challenge: Emergent misalignment is a problem for large language models (LLMs) fine-tuning on narrow tasks can induce harmful behaviors despite no explicit supervision.
Approach: They propose a mechanistic account based on the geometry of feature superposition . they propose to use sparse autoencoders to identify misalignment-inducing features .
Outcome: The proposed model outperforms random removal and stronger mitigations than LLM-as-a-judge filtering.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations