Pith. sign in

REVIEW 3 cited by

Mitigating Catastrophic Forgetting in Language Transfer via Model Merging

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.08699 v2 pith:KOTMXGBX submitted 2024-07-11 cs.LG

classification cs.LG
keywords forgettingmodeldomainlanguagemodelsacrossadaptationcatastrophic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As open-weight large language models (LLMs) achieve ever more impressive performances across a wide range of tasks in English, practitioners aim to adapt these models to different languages. However, such language adaptation is often accompanied by catastrophic forgetting of the base model's capabilities, severely limiting the usefulness of the resulting model. We address this issue by proposing Branch-and-Merge (BaM), a new adaptation method based on iteratively merging multiple models, fine-tuned on a subset of the available training data. BaM is based on the insight that this yields lower magnitude but higher quality weight changes, reducing forgetting of the source domain while maintaining learning on the target domain. We demonstrate in an extensive empirical study on Bulgarian and German that BaM can significantly reduce forgetting while matching or even improving target domain performance compared to both standard continued pretraining and instruction finetuning across different model architectures.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Execution-driven bootstrapping, where a model generates SQL, executes it, and keeps only queries that run, lets a 7B model outperform GPT-4o on PostgreSQL, MySQL, and Oracle text-to-SQL benchmarks.

  2. SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment

    cs.CL 2025-09 conditional novelty 5.0 of 10

    Adding a KL penalty between fine-tuned and original model logits on input tokens during RAG fine-tuning reduces catastrophic forgetting while preserving downstream performance.

  3. Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Neuron-Fusion selectively restores large-change neurons from a fine-tuned multimodal model and suppresses small changes, improving language retention with modest visual trade-offs.

Pith tools