Structured output may cut answer diversity across 44 language models
vista8 · x · 2026-07-27
A new paper claims that asking language models for structured output can reduce answer diversity across many models.
- The study re-runs the One-Word Census on 44 models, comparing unconstrained prompts with requests such as “Reply with JSON only.”
- Under JSON requests, the modal answer share rises from 41% to 64%, distinct answers drop from 52 to 36, and mean answer-choice surprisal falls from 1.80 to 1.58 bits.
- The authors argue the effect is progressive, largely tied to the format register rather than the decoder itself: JSON and XML show the strongest compression, while YAML and CSV do not show the same effect.
- They conclude that structured output makes models converge more toward the mode, meaning software systems that depend on schema-filled responses may see less diversity than chat evaluation suggests.
Related event: Structured Outputs Reduce LLM Diversity, Study Finds(2 posts)→
More from Research
- NVIDIA releases Molt, a PyTorch-native framework for agentic RL — dair_ai · 2026-07-27
- ICML 2025 paper shows denoising models can raise spatial reasoning accuracy from under 1% to over 50% — CSProfKGD · 2026-07-27
- AI One-Shots 25k Lines of Code to Simulate Black Hole Electrodynamics in 5 Minutes — kylekabasares · 2026-07-27
- AutoScientist challenge asks systems to optimize training toward any objective — sarahookr · 2026-07-27
- Paper proposes Continuous SUN for evaluating inorganic crystal generators — CatAstro_Piyush · 2026-07-27
- Kimi K3 triples parameters and doubles active experts in a new MoE design — teortaxesTex · 2026-07-27