knowledge-editing-methods-such-rome-fine-tuning-insert-stated-fact-reliably CLM-0308mechanismsingle paperReviewed by AI
Knowledge-editing methods such as ROME and fine-tuning insert a stated fact reliably but do not carry its logical consequences: on multi-hop questions generated from knowledge-graph rules that the edit entails, accuracy is up to 24 points lower than on the directly edited fact, so an edited model can assert a new fact and still answer as if its implications never changed.
Capability: Absorbing and flexibly using new knowledge
Observed on
Rule-derived multi-hop questions from a knowledge graph around each edit, ROME and FT among others, 2026; open models..
Sources
- Consistent with the older ripple-effect literature; the rule-based construction makes the entailments precise. Methods tested are classic locate-and-edit and FT, not retrieval-based editing.
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- A single fact edit exerts two coupled pressures on its knowledge neighbourhood, propagation to facts that should change and leakage into facts that should not, and planning the edit's target representations jointly under both constraints, with a gate that rejects risky plans before touching parameters, improved propagation and preservation on RippleEdits by at least 7% across backbones over methods that treat the two separately.Absorbing and flexibly using new knowledge · reviewed by AI
- When new knowledge is a set of interconnected fictional future events rather than isolated fact edits, updating 4-8B instruct models by mid-training on teacher-generated long-form articles plus preference tuning (preferring reasoned answers over outdated, hallucinated, or needlessly abstaining ones) beats graph-retrieval and in-context editing baselines on multi-hop and causal questions, while remaining worse than in-context methods on exact numeric single-hop recall unless retrieved facts are also supplied.Absorbing and flexibly using new knowledge · reviewed by AI
- When a language model is updated by fine-tuning on a substituted fact, the facts it already answered correctly that are most likely to flip to wrong are those whose answer entity is referenced by many other facts, and updates to such structurally popular facts corrupt connected facts out to five hops in the fact graph — so popularity, not long-tail rarity, predicts collateral corruption among already-correct knowledge.Stating false facts confidently · reviewed by AI
- In LLM fact-checking over supplied evidence, high veracity accuracy does not imply the verdict depends on that evidence: when the model's own cited sentences are iteratively removed, off-the-shelf models (GPT-4o-mini, Gemini-2.5-Flash-Lite, Qwen-2.5-32B, Llama-3.1-8B) keep their SUPPORT/REFUTE labels at a non-zero plateau instead of abstaining, and training with paired supervision that requires NOT_ENOUGH_INFO on the evidence-ablated input removes most of that persistence without losing accuracy.Checking claims against evidence · reviewed by AI
- On 1,010 counterfactual edits rooted in Chinese cultural entities and aligned with English counterparts, an edit made in one language largely does not propagate to the other: edits succeed in the edited language (about 80% for Chinese at batch size 10, falling with batch size) while the other language keeps answering the old fact, so multilingual models store the same fact in language-specific ways that editing does not bridge.Absorbing and flexibly using new knowledge · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: An editing method whose entailed-fact accuracy matches direct-fact accuracy on this benchmark.