Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs

Documenti analoghi

• Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL
  di: Zhong, Qihuang, et al.
  Pubblicazione: (2024)
• KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance
  di: Zhong, Qihuang, et al.
  Pubblicazione: (2025)
• ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding
  di: Zhong, Qihuang, et al.
  Pubblicazione: (2024)
• ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering
  di: Zhu, Yikai, et al.
  Pubblicazione: (2026)
• E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation
  di: Zhong, Qihuang, et al.
  Pubblicazione: (2022)