Pith. sign in

Model Editing by Standard Fine-Tuning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Standard fine-tuning is considered not as effective as specialized methods for model editing due to its comparatively poor performance. However, it is simple, agnostic to the architectural details of the model being edited, and able to leverage advances in standard training techniques with no additional work (e.g., black-box PEFT for computational efficiency), making it an appealing choice for a model editor. In this work, we show that standard fine-tuning alone can yield competitive model editing performance with two minor modifications. First, we optimize the conditional likelihood rather than the full likelihood. Second, in addition to the typical practice of training on randomly paraphrased edit prompts to encourage generalization, we also train on random or similar unedited facts to encourage locality. Our experiments on the ZsRE and CounterFact datasets demonstrate that these simple modifications allow standard fine-tuning to match or outperform highly specialized editors in terms of edit score.

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Memorization and Knowledge Injection in Gated LLMs

cs.CL · 2025-04-30 · conditional · novelty 6.0

MEGa injects episodic memories into separate gated LoRA adapters selected by embedding similarity, mitigating catastrophic forgetting and enabling recall, QA, and compositional questions on two datasets.

citing papers explorer

Showing 1 of 1 citing paper.

  • Memorization and Knowledge Injection in Gated LLMs cs.CL · 2025-04-30 · conditional · none · ref 19 · internal anchor

    MEGa injects episodic memories into separate gated LoRA adapters selected by embedding similarity, mitigating catastrophic forgetting and enabling recall, QA, and compositional questions on two datasets.