Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models

Documenti analoghi

• Unraveling Babel: Exploring Multilingual Activation Patterns of LLMs and Their Applications
  di: Liu, Weize, et al.
  Pubblicazione: (2024)
• Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation
  di: Chen, Qiyuan, et al.
  Pubblicazione: (2025)
• From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs
  di: Li, Guocong, et al.
  Pubblicazione: (2025)
• OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models
  di: Xu, Hainiu, et al.
  Pubblicazione: (2024)
• Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling
  di: Chen, Qiyuan, et al.
  Pubblicazione: (2026)