Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation

Documenti analoghi

• Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling
  di: Chen, Qiyuan, et al.
  Pubblicazione: (2026)
• CC-GSEO-Bench: A Content-Centric Benchmark for Measuring Source Influence in Generative Search Engines
  di: Chen, Qiyuan, et al.
  Pubblicazione: (2025)
• Curing Semantic Drift: A Dynamic Approach to Grounding Generation in Large Vision-Language Models
  di: Chen, Jiahe, et al.
  Pubblicazione: (2025)
• MM-DADM: Multimodal Drug-Aware Diffusion Model for Virtual Clinical Trials
  di: Shao, Qian, et al.
  Pubblicazione: (2025)
• Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models
  di: Liu, Weize, et al.
  Pubblicazione: (2023)