All Quiet on the Neural Front: Language Models Do Not Report Injected Pain States
cs.CL, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-12
Terminology
Sources
- The Pain Axis: LLMs Represent Self-Directed Harm and Act on It
- Emergent Introspective Awareness in Large Language Models
- Mechanisms of Introspective Awareness
- Emergent Introspection in AI is Content-Agnostic
- Detecting the Disturbance: A Nuanced View of Introspective Abilities in LLMs
- Latent Introspection: Models Can Detect Prior Concept Injections
- Representation Engineering: A Top-Down Approach to AI Transparency
- Steering Language Models With Activation Engineering
- Steering Llama 2 via Contrastive Activation Addition
- Steering Awareness: Detecting Activation Steering from Within
- Can LLMs Introspect? A Reality Check
- Don't Ask: Understanding What Numeric Self-Reports Measure in Language Models
- Refusal in Language Models Is Mediated by a Single Direction
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data