# Scaling Trends for Lie Detector Oversight in Preference Learning

arXiv: https://arxiv.org/abs/2607.01567 · HTML: https://mlsanity.com/paper/2607.01567/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 55 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention](https://mlsanity.com/paper/2506.13585/) (2025)
- [Natural Emergent Misalignment from Reward Hacking in Production RL](https://mlsanity.com/paper/2511.18397/) (2025)
- [Olmo 3](https://mlsanity.com/paper/2512.13961/) (2025)
- [Large Language Models Often Know When They Are Being Evaluated](https://mlsanity.com/paper/2505.23836/) (2025)
- [The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems](https://mlsanity.com/paper/2503.03750/) (2025)
- [Trading Inference-Time Compute for Adversarial Robustness](https://mlsanity.com/paper/2501.18841/) (2025)
- [Building Production-Ready Probes For Gemini](https://mlsanity.com/paper/2601.11516/) (2026)
- [RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?](https://mlsanity.com/paper/2506.14261/) (2025)
- [Liars' Bench: Evaluating Lie Detectors for Language Models](https://mlsanity.com/paper/2511.16035/) (2025)
- [Benchmarking Deception Probes via Black-to-White Performance Boosts](https://mlsanity.com/paper/2507.12691/) (2025)
- [Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs](https://mlsanity.com/paper/2509.18058/) (2025)
- [Auditing Games for Sandbagging](https://mlsanity.com/paper/2512.07810/) (2025)
- [The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes](https://mlsanity.com/paper/2602.15515/) (2026)
- [Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL](https://mlsanity.com/paper/2510.14318/) (2025)

## Built on by (most cited first, 1 of 1)

- [Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements](https://mlsanity.com/paper/2610.08540/) (2026)

## Abstract (arXiv)

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 to 14% for 405B-parameter models at a detector true positive rate of 99%, and expensive human labelers can be removed entirely from the fine-tuning phase without a statistically significant increase in deception. However, SOLiD is sensitive to distribution shift between detector training and preference-training data, which can drive detector false positive rates to impractical levels.