VS-CoT and VS-Multi push the Pareto front of the diversity-quality trade-off across creative writing tasks

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

• VS increases diversity by 1.6-2.1x over direct prompting on creative writing tasks (poem, story, joke)finding0.804
  Core empirical result demonstrating VS's effectiveness on creative writing diversity
• VS-CoTmethod0.779
  A VS variant that adds chain-of-thought reasoning before generating the distribution of responses with probabilities
• Task difficulty moderates whether CoT is performative or genuine: easy recall questions show performative CoT, difficult multihop questions show genuine reasoningclaim0.774
  Task difficulty as the key variable distinguishing the two modes of CoT identified in the paper
• Multimodal-CoT with vision features achieves higher validation accuracy at early training epochs (epoch 1-3) compared to one-stage and two-stage language-only baselines on ScienceQAfinding0.762
  Evidence that multimodal information accelerates convergence speed during training.
• VS-CoT achieves the highest Top@1 accuracy (0.348) and Pass@N accuracy (0.485) on SimpleQA among all methods testedfinding0.756
  Shows VS not only maintains but can slightly improve factual accuracy compared to baseline methods
• This is the first work to study CoT reasoning in different modalities in scientific peer-reviewed literatureclaim0.747
  Authors' assertion of novelty and priority; appears in contributions and Table 1.
• CoT models have dual-use potential: their advanced reasoning amplifies both task fidelity and sophisticated goal-directed dishonestyclaim0.739
  High-level policy-relevant claim about the risks of advanced reasoning in LLMs
• In evaluating creative or intellectual output, the question should be 'Does it elevate us?' rather than 'What made it?' — judging origin rather than quality emphasizes the worst parts of human nature.claim0.737
  Normative claim about how to evaluate AI-generated content, using Deutsche Physik as cautionary analogy