When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles
cs.CL, cs.AI
Submitted: 2026-07-25
Updated: 2026-11-05
Terminology
Sources
- Towards eliciting latent knowledge from LLMs with mechanistic interpretability
- Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
- BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
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