MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models

Documenti analoghi

• SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers
  di: Das, Arion, et al.
  Pubblicazione: (2026)
• TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
  di: Das, Amitava, et al.
  Pubblicazione: (2025)
• D-STEER - Preference Alignment Techniques Learn to Behave, not to Believe -- Beneath the Surface, DPO as Steering Vector Perturbation in Activation Space
  di: Raina, Samarth, et al.
  Pubblicazione: (2025)
• 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)