$π^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models

Documenti analoghi

• SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
  di: Pham, Thinh, et al.
  Pubblicazione: (2025)
• ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases
  di: Do, Quyet V., et al.
  Pubblicazione: (2024)
• NeuroProlog: Multi-Task Fine-Tuning for Neurosymbolic Mathematical Reasoning via the Cocktail Effect
  di: Zunjare, Pratibha, et al.
  Pubblicazione: (2026)
• VLegal-Bench: Cognitively Grounded Benchmark for Vietnamese Legal Reasoning of Large Language Models
  di: Dong, Nguyen Tien, et al.
  Pubblicazione: (2025)
• A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences
  di: Zunjare, Pratibha, et al.
  Pubblicazione: (2025)