method
active
method:strange-stories-task

Strange Stories Task

ToM task requiring advanced mentalizing such as interpreting lies; unique in having 3 scores (0/1/2).

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.

  • Task Difficultyconcept0.727
    The paper identifies task difficulty as a key moderator: easy MMLU questions show performative CoT, hard GPQA-Diamond questions show genuine reasoning
  • Classic ToM test requiring understanding that another agent holds a belief different from reality; scored 0/1.
  • Hinting Taskmethod0.702
    One of four ToM tasks analyzed; requires inferring speaker intent from indirect hints; scored 0/1.
  • Strange Loopconcept0.696
    Self-referential feedback structure enabling thought patterns to scale up and reify themselves as independent thinkers.
  • Task providing scenario prompts for LLMs to write essays reflecting personality traits
  • Novel task asking which of two sentences received a stronger injection, using matched-pairs design to control for positional bias
  • Novel task asking which of 10 sentences received injection, cycling injection through all positions to average out positional bias
  • Task balancingconcept0.683
    The problem of ensuring all tasks in MTL perform well, avoiding dominance by some tasks.