Hit the Sweet Spot! Span-Level Ensemble for Large Language Models

Documenti analoghi

• LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs
  di: Chen, Jianghao, et al.
  Pubblicazione: (2025)
• Bridging the Gap between Different Vocabularies for LLM Ensemble
  di: Xu, Yangyifan, et al.
  Pubblicazione: (2024)
• Diver: Large Language Model Decoding with Span-Level Mutual Information Verification
  di: Lu, Jinliang, et al.
  Pubblicazione: (2024)
• Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation
  di: Wu, Junhong, et al.
  Pubblicazione: (2024)
• LR^2Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems
  di: Chen, Jianghao, et al.
  Pubblicazione: (2025)