TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation

Documenti analoghi

• What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworks
  di: Huang, Chengrui, et al.
  Pubblicazione: (2024)
• CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis
  di: Feng, Ruixiang, et al.
  Pubblicazione: (2025)
• Evolution without Large Models: Training Language Model with Task Principles
  di: Zhu, Minghang, et al.
  Pubblicazione: (2025)
• Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization
  di: Cui, Chaoqun, et al.
  Pubblicazione: (2025)
• Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation
  di: Zhu, Dongsheng, et al.
  Pubblicazione: (2025)