single-fact-edit-exerts-two-coupled-pressures-knowledge-neighbourhood CLM-0324mechanismsingle paperReviewed by AI
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.
Capability: Absorbing and flexibly using new knowledge
Observed on
RippleEdits and ZsRE on LLaMA-3, GPT-J and Qwen2.5-Instruct, 2026; locate-and-edit family; gains 7-30% by metric and backbone..
Sources
- Validated by: Propagation, preservation, specificity and consistency metrics on RippleEdits and ZsRE against SAKE and other baselines across three backbones; fluency drops at most 1.5%.. Method paper with the usual own-baseline comparison; the framing of coupled propagation/leakage pressure is the reusable idea.
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
- 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.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models by mid-training on teacher-generated long-form articles plus preference tuning (preferring reasoned answers over outdated, hallucinated, or needlessly abstaining ones) beats graph-retrieval and in-context editing baselines on multi-hop and causal questions, while remaining worse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 long chain of thought is verified by classifying a graph of its steps, the predictive signal comes almost entirely from the semantic content of the steps, not the graph shape: replacing step embeddings with purely structural metadata (child/parent counts, chain index, position) drops accuracy to near chance on math, science and multiple-choice reasoning, while remaining above chance only on code.Carrying a chain of inference through to its conclusion · reviewed by AI
- General-purpose factuality verifiers (entailment-, consistency-, and RAG-trained) and zero-shot frontier LLM judges perform near chance at spotting unsupported claims in scientific peer reviews that must be checked against the full submitted paper, because they cannot separate paper-unsupported assertions from legitimate evaluative critique; small models fine-tuned on in-domain examples beat them by a wide margin.Stating false facts confidently · reviewed by AI
- As long as trusted instructions and untrusted retrieved content occupy the same model context, defenses that only change how untrusted text is marked or weighted (instruction hierarchies, spotlighting, content detectors) reduce indirect-injection success but do not remove it; only defenses that isolate contexts or restrict the action set give guarantees, at a cost in the agent's ability to combine information across sources.Following instructions hidden in data · 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: Neighbourhood sizes or edit batches where the joint objective fails to scale, or preservation gains that vanish on held-out unrelated facts.