TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

Documenti analoghi

• AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization
  di: Das, Amitava, et al.
  Pubblicazione: (2025)
• ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment
  di: Wanaskar, Kapil, et al.
  Pubblicazione: (2026)
• AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints
  di: Roy, Aniruddha, et al.
  Pubblicazione: (2025)
• Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LLMs
  di: Saha, Anusa, et al.
  Pubblicazione: (2026)
• MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
  di: Saha, Partha Pratim, et al.
  Pubblicazione: (2026)