DTCA framework enhances mathematical reasoning ability of diffusion language models
The story so far
The DTCA framework performs credit assignment at the label level through confidence enhancement and entropy calibration, improving the mathematical reasoning ability of diffusion language models. The framework's experiments on LLaDA-8B-Instruct show significant performance improvement in mathematical reasoning under different generation budgets, with the MATH500 metric increasing by 9.0 points and the GSM8K metric improving by 5.3 points.
AI-written from the reports · Updated 21 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersDTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models
DTCA performs label-level credit assignment through confidence enhancement and entropy calibration, improving the mathematical reasoning ability of diffusion language models. The framework, when tested on LLaDA-8B-Instruct, shows significant performance improvement in mathematical reasoning under different generation budgets, with the MATH500 metric increasing by 9.0 points and the GSM8K metric improving by 5.3 points.