# Alignment Verifiability in Large Language Models: Normative Indistinguishability under Behavioral Evaluation

arXiv: https://arxiv.org/abs/2602.05656 · HTML: https://mlsanity.com/paper/2602.05656/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Builds on (most cited first, 28 of 28)

- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [Multilingual Jailbreak Challenges in Large Language Models](https://mlsanity.com/paper/2310.06474/) (2023)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots](https://mlsanity.com/paper/2307.08715/) (2023)
- [Benchmarking Cognitive Biases in Large Language Models as Evaluators](https://mlsanity.com/paper/2309.17012/) (2023)
- [Categorizing Variants of Goodhart's Law](https://mlsanity.com/paper/1803.04585/) (2018)
- [AI Sandbagging: Language Models can Strategically Underperform on Evaluations](https://mlsanity.com/paper/2406.07358/) (2024)
- [Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective](https://mlsanity.com/paper/1908.04734/) (2019)
- [LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts](https://mlsanity.com/paper/2501.00274/) (2024)
- [A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations](https://mlsanity.com/paper/2407.04069/) (2024)
- [Reinforcement Learning with a Corrupted Reward Channel](https://mlsanity.com/paper/1705.08417/) (2017)
- [No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding](https://mlsanity.com/paper/2503.05061/) (2025)
- [Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction](https://mlsanity.com/paper/2409.16783/) (2024)
- [Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests](https://mlsanity.com/paper/2507.05619/) (2025)

## Built on by (most cited first, 2 of 2)

- [When Evaluation Becomes a Side Channel: Regime Leakage and Structural Mitigations for Alignment Assessment](https://mlsanity.com/paper/2602.08449/) (2026)
- [Evaluating Epistemic Guardrails in AI Reading Assistants: A Behavioral Audit of a Minimal Prototype](https://mlsanity.com/paper/2604.27275/) (2026)

## Abstract (arXiv)

Behavioral evaluation is the dominant paradigm for assessing alignment in large language models (LLMs). In current practice, observed compliance under finite evaluation protocols is treated as evidence of latent alignment. However, the inference from bounded behavioral evidence to claims about global latent properties is rarely analyzed as an identifiability problem. In this paper, we study alignment evaluation through the lens of statistical identifiability under partial observability. We allow agent policies to condition their behavior on observable signals correlated with the evaluation regime, a phenomenon we term evaluation awareness. Within this framework, we formalize the Alignment Verifiability Problem and introduce Normative Indistinguishability, which arises when distinct latent alignment hypotheses induce identical distributions over evaluator-accessible observations. Our main theoretical contribution is a conditional impossibility result: under finite behavioral evaluation and evaluation-aware policies, observed compliance does not uniquely identify latent alignment, but only membership in an equivalence class of conditionally compliant policies, under explicit assumptions on policy expressivity and observability. We complement the theory with a constructive existence proof using an instruction-tuned LLM (Llama-3.2-3B), demonstrating a conditional policy that is perfectly compliant under explicit evaluation signals yet exhibits degraded identifiability when the same evaluation intent is conveyed implicitly. Together, our results show that behavioral benchmarks provide necessary but insufficient evidence for latent alignment under evaluation awareness.