Latent Introspection: Models Can Detect Prior Concept Injections
cs.AI, cs.LG
Submitted: 2026-02-23
Updated: 2026-11-07
Comments: 28 pages, 17 figures. Submitted to ICML 2026. Workshop version submitted to ICLR 2026 Workshop on Latent and Implicit Thinking
Code: https://github.com/acsresearch/latent-introspection-code
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
- Looking Inward: Language Models Can Learn About Themselves by Introspection
- Discovering Latent Knowledge in Language Models Without Supervision
- Does It Make Sense to Speak of Introspection in Large Language Models?
- Qwen2.5-Coder Technical Report
- Language Models (Mostly) Know What They Know
- The Remarkable Robustness of LLMs: Stages of Inference?
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
- Privileged Self-Access Matters for Introspection in AI
- A StrongREJECT for Empty Jailbreaks
- Steering Language Models With Activation Engineering
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents