Serghei Brinza

The Second Loop: Durable Correction of Memorized Errors in Frozen Language Models

A frozen language model that has memorized a wrong fact repeats it even when the correct fact is placed in its context. We study whether such an error can be corrected durably — surviving a full process reload — without touching a single weight, and where the criterion of truth f...

The Second Loop: Durable Correction of Memorized Errors in Frozen Language Models

A frozen language model that has memorized a wrong fact repeats it even when the correct fact is placed in its context. We study whether such an error can be corrected durably — surviving a full process reload — without touching a single weight, and where the criterion of truth f...