Model change

When a single conversation involves different models, e.g., routing between standard and reasoning models

Neighborhood — ranked by edge-count

paper

concept

model
related_to
A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.

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 Editingconcept0.848
Technique for modifying model knowledge or behavior via targeted interventions, e.g., ROME by Meng et al.
model selectionconcept0.817
Comparing models using log-evidence approximated by free energy.
Manual model editingconcept0.803
Ability to surgically alter model behavior through direct parameter changes rather than activation interventions.
Language Modelsconcept0.793
Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
Language Modelconcept0.787
Primary test domain for manifold steering, including reasoning and ICL tasks
Manual model editing through parameter manipulationconcept0.786
Application enabled by VPD: direct manipulation of weight matrices for interpretable model modification.
Model Steeringconcept0.784
Using interventions to guide model generation behavior, e.g., adding sentiment vectors at inference time
Preference Modelframework0.780
A model trained on comparison data to assign scores to responses, used as reward signal in RLHF/RLAIF.