UniCreative uses reference-free RL with an adaptive constraint-aware reward model to unify long-form coherence and short-form creativity in AI writing, producing an emergent ability to switch between planning and direct generation.
Ruizhe Li, Chiwei Zhu, Benfeng Xu, Xiaorui Wang, and Zhendong Mao
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
LLM translations introduce model-specific statistically significant emotional fingerprints that limit preservation of author voice, with post-editing providing partial alignment to human norms.
DEFINED is a data-efficient AI framework that uses a hierarchical eight-dimensional metric and mixed-granularity training on a pre-trained autoregressive LM to score debate creativity accurately from limited expert annotations.
IDEAFix is an evaluation framework that varies task attributes and defixation prompts in LLM idea generation, showing task formulation affects performance while simple prompts boost originality but homogenization persists.
citing papers explorer
-
UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning
UniCreative uses reference-free RL with an adaptive constraint-aware reward model to unify long-form coherence and short-form creativity in AI writing, producing an emergent ability to switch between planning and direct generation.
-
Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing
LLM translations introduce model-specific statistically significant emotional fingerprints that limit preservation of author voice, with post-editing providing partial alignment to human norms.
-
DEFINED: A Data-Efficient Computational Framework for Fine-Grained Creativity Assessment in Debate Scenarios
DEFINED is a data-efficient AI framework that uses a hierarchical eight-dimensional metric and mixed-granularity training on a pre-trained autoregressive LM to score debate creativity accurately from limited expert annotations.
-
IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs
IDEAFix is an evaluation framework that varies task attributes and defixation prompts in LLM idea generation, showing task formulation affects performance while simple prompts boost originality but homogenization persists.