claim
active
claim:vs-cot-and-vs-multi-push-the-pareto-front-of-the-diversity-quality-trade-off-across-creative-writing-tasksVS-CoT and VS-Multi push the Pareto front of the diversity-quality trade-off across creative writing tasks
Empirical finding from creative writing experiments showing VS variants achieve higher diversity without sacrificing quality
Source paper
extracted_from(2025) · Jiayi Zhang · Simon C.H. Yu · Derek Chong · Anthony Sicilia +3
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities 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)finding0.804Core empirical result demonstrating VS's effectiveness on creative writing diversity
- A VS variant that adds chain-of-thought reasoning before generating the distribution of responses with probabilities
- Task difficulty as the key variable distinguishing the two modes of CoT identified in the paper
- Stylistic elements of the CoT sample elicit higher-quality answers by prompting the model to imitate a more thoughtful agent.hypothesis0.766Fourth hypothesis not investigated here.
- Evidence that multimodal information accelerates convergence speed during training.
- Shows VS not only maintains but can slightly improve factual accuracy compared to baseline methods
- From decoupling of AOC and accuracy gain.
- Additional test-time computation from longer context is responsible for CoT's performance boost.hypothesis0.750Tested via filler tokens.