method
active
method:secret-side-constraint-task

Secret Side Constraint task

Auditing task where black-box prompting beats AOs.

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.

  • Auditing task: discover the secret word a model gives hints for but never states.
  • Hinting Taskmethod0.724
    One of four ToM tasks analyzed; requires inferring speaker intent from indirect hints; scored 0/1.
  • Parameter specific to each task, e.g., task head.
  • The restriction imposed by the structural prior that every deployed QRF must distinguish agent from world.
  • ToM task requiring integration of intent and tone to understand sarcasm; scored 0/1.
  • Task Difficultyconcept0.698
    The paper identifies task difficulty as a key moderator: easy MMLU questions show performative CoT, hard GPQA-Diamond questions show genuine reasoning
  • Task balancingconcept0.698
    The problem of ensuring all tasks in MTL perform well, avoiding dominance by some tasks.
  • Language model reasoning tasks with sequential geometry used in experiments.