Scaling Trends for Lie Detector Oversight in Preference Learning

Summary

arXiv:2607.01567v1 Announce Type: new Abstract: Deceptive behavior in LLMs is costly to monitor and prevent, motivating approaches such as Scalable Oversight via Lie Detectors (SOLiD) (Cundy & Gleave, 2025), which uses lie detectors to identify responses for review by high-cost labelers. In this paper, we scale SOLiD to larger models and evaluate it in more diverse and realistic preference-learning settings. We find favorable scaling: undetected deception drops from 34% for 1B-parameter models t

SpinGraph analysis pending — check back after processing.

• Profit-Based Counterfactual Explanations for Product Improvement: A Case Study of Manga Sales in Japan
• SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication
• Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model
• Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation
• EO-Agents: A Three-Agent LLM Pipeline for Earth Observation Hypothesis Generation
• OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration