S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs

Documenti analoghi

• From Latent Signals to Reflection Behavior: Tracing Meta-Cognitive Activation Trajectory in R1-Style LLMs
  di: Du, Yanrui, et al.
  Pubblicazione: (2026)
• Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain
  di: Du, Yanrui, et al.
  Pubblicazione: (2023)
• Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint
  di: Du, Yanrui, et al.
  Pubblicazione: (2025)
• Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak
  di: Du, Yanrui, et al.
  Pubblicazione: (2023)
• MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
  di: Du, Yanrui, et al.
  Pubblicazione: (2024)