Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution

Documenti analoghi

• LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
  di: Stengel-Eskin, Elias, et al.
  Pubblicazione: (2024)
• DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning
  di: Sivakumaran, Nithin, et al.
  Pubblicazione: (2025)
• Teaching Models to Balance Resisting and Accepting Persuasion
  di: Stengel-Eskin, Elias, et al.
  Pubblicazione: (2024)
• UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
  di: Patil, Vaidehi, et al.
  Pubblicazione: (2025)
• Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns
  di: Xiao, Hanqi, et al.
  Pubblicazione: (2025)