fine-tuning-retention · proposed

Retaining skills and safety after fine-tuning

Proposed. Several papers in the review queue converged on this framing, so the pipeline added it. Nobody has decided it is the right way to carve up the subject — it may be two topics, or a duplicate of another, or not a topic at all. Saying so is useful.

Covers loss of general capability, out-of-domain skill, or refusal behavior caused by domain, multimodal, or alignment fine-tuning; excludes in-domain accuracy gains and inference-time behavior shifts.

Tags: general

Proposed from the ingestion pipeline rather than chosen by hand. 5 papers in the review queue independently pointed at this same competence, arriving under 4 different names (catastrophic-forgetting, alignment-tax, multimodal-adaptation-forgetting, finetuning-alignment- fragility), which is the signal that it is a real recurring topic and not one author's framing. Recurs across four independent framings (capability forgetting and safety erosion) and is not covered by any existing entry.

What counts as this capability

Scope boundary used when deciding whether a paper is really about this capability, rather than merely mentioning it.

Covers loss of general capability, out-of-domain skill, or refusal behavior caused by domain, multimodal, or alignment fine-tuning; excludes in-domain accuracy gains and inference-time behavior shifts.

Claims

No claims filed yet.

Techniques

None yet.

Suggest a change

Capabilities are a way of carving up the subject, and carvings are arguable. Say so if this one is wrong — especially a proposed one, which a pipeline added because several papers used the same framing, not because anyone decided it was right.