Probing the Misaligned Thinking Process of Language Models
Quick Answer
This study identifies 18 misalignment indicators in large language models, achieving a 0.935 AUROC on out-of-distribution benchmarks while maintaining low false positives.
Quick Take
The approach involves monitoring cognitive processes through linear probes, crucial for ensuring safe deployment in high-stakes environments.
Key Points
- Developed a taxonomy of 18 indicators for misaligned behaviors in language models.
- Achieved 0.935 AUROC on out-of-distribution benchmarks with low false positive rates.
- Utilized linear probes to detect misalignment in internal model activations.
- Created an automated pipeline for generating multi-turn training conversations.
- Conducted in-depth analysis of model representations related to misalignment.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation. As they are increasingly deployed in high-stakes settings, it is critical to reliably detect such behaviors to ensure safe and responsible use. In this work, we propose to monitor misalignment by decomposing it into fine-grained cognitive processes -- misalignment indicators -- and detecting their presence in a model's internal activations via linear probes. We develop a taxonomy of 18 indicators spanning different misaligned behaviors, paired with an automated, meta-plan-guided pipeline that generates multi-turn training conversations. To rigorously evaluate generalization, we construct an out-of-distribution suite combining automated behavioral elicitation, established misalignment benchmarks, and natural benign conversations. Across 5 misaligned behaviors, our probes match a strong LLM judge with 0.935 AUROC on out-of-distribution benchmarks while keeping a low false positive rate on benign traffic. We further perform in-depth analysis to understand the probes and the model's internal representations of misalignment indicators.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.24251 [cs.AI] |
| (or arXiv:2606.24251v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.24251 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kaiwen Zhou [view email]
[v1]
Tue, 23 Jun 2026 07:40:28 UTC (917 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.