Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs
cs.LG, cs.AI, cs.CL, cs.ET, cs.NE
Submitted: 2026-05-30
Updated: 2026-05-30
Terminology
Sources
- Understanding intermediate layers using linear classifier probes
- Discovering Latent Knowledge in Language Models Without Supervision
- INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
- The Llama 3 Herd of Models
- Mistral 7B
- Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
- Qwen2.5 Technical Report
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis