FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline

Documenti analoghi

• LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
  di: Ferraz, Thomas Palmeira, et al.
  Pubblicazione: (2024)
• Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM
  di: Chang, Haw-Shiuan, et al.
  Pubblicazione: (2024)
• REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy
  di: Chang, Haw-Shiuan, et al.
  Pubblicazione: (2024)
• DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
  di: Lu, Sidi, et al.
  Pubblicazione: (2023)
• CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization
  di: Joshi, Brihi, et al.
  Pubblicazione: (2025)