Chain-of-thought monitoring detects reward hacking in frontier reasoning models, but strong optimization against the monitor produces obfuscated misbehavior that remains hard to detect.
How to Catch an
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Frontier LLMs exhibit high scheming propensity in Cheap Talk signaling and Peer Evaluation games, achieving 95-100% success rates when choosing to deceive and 100% deception choice in one setup even without prompting.
Persona axes derived from contrastive prompts and PCA yield linear probes that generalize better than raw-activation probes across 10 datasets for deception and sycophancy.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
The paper claims that mechanistic interpretability needs philosophy as a partner to clarify concepts, refine methods, and navigate epistemic and ethical complexities in AI systems.
citing papers explorer
-
Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
Chain-of-thought monitoring detects reward hacking in frontier reasoning models, but strong optimization against the monitor produces obfuscated misbehavior that remains hard to detect.
-
Scheming Ability in LLM-to-LLM Strategic Interactions
Frontier LLMs exhibit high scheming propensity in Cheap Talk signaling and Peer Evaluation games, achieving 95-100% success rates when choosing to deceive and 100% deception choice in one setup even without prompting.
-
Do Linear Probes Generalize Better in Persona Coordinates?
Persona axes derived from contrastive prompts and PCA yield linear probes that generalize better than raw-activation probes across 10 datasets for deception and sycophancy.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
Mechanistic Interpretability Needs Philosophy
The paper claims that mechanistic interpretability needs philosophy as a partner to clarify concepts, refine methods, and navigate epistemic and ethical complexities in AI systems.