method
active
method:model-knowledge-editing-rome

Model (knowledge) editing / ROME

Precise knowledge modification; ROME has flaws.

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Model Editingconcept0.818
    Technique for modifying model knowledge or behavior via targeted interventions, e.g., ROME by Meng et al.
  • modelconcept0.799
    A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
  • Ability to surgically alter model behavior through direct parameter changes rather than activation interventions.
  • Model Evidenceconcept0.776
    Probability of data under the model, penalizing complexity and rewarding accuracy.
  • Application enabled by VPD: direct manipulation of weight matrices for interpretable model modification.
  • Language Modelconcept0.771
    Primary test domain for manifold steering, including reasoning and ICL tasks
  • Model changeconcept0.770
    When a single conversation involves different models, e.g., routing between standard and reasoning models
  • Language Modelsconcept0.768
    Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.