# SpecEval: Evaluating Model Adherence to Behavior Specifications

arXiv: https://arxiv.org/abs/2509.02464 · HTML: https://mlsanity.com/paper/2509.02464/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 1 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Built on by (most cited first, 9 of 9)

- [Stress-Testing Model Specs Reveals Character Differences among Language Models](https://mlsanity.com/paper/2510.07686/) (2025)
- [The Compliance Gap: Why AI Systems Promise to Follow Process Instructions but Don't](https://mlsanity.com/paper/2605.01771/) (2026)
- [The Stability Trap: Evaluating the Reliability of LLM-Based Instruction Adherence Auditing](https://mlsanity.com/paper/2601.11783/) (2026)
- [Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs](https://mlsanity.com/paper/2604.07655/) (2026)
- [Self-CTRL: Self-Consistency Training with Reinforcement Learning](https://mlsanity.com/paper/2606.18327/) (2026)
- [DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance](https://mlsanity.com/paper/2608.14644/) (2026)
- [Offscript: Automated Auditing of Instruction Adherence in LLMs](https://mlsanity.com/paper/2512.10172/) (2025)
- [A Roadmap to Impactful Pluralistic Alignment Research](https://mlsanity.com/paper/2607.22305/) (2026)
- [Detecting Inconsistencies in Model Specifications with LLM-as-Verifier Reasoning](https://mlsanity.com/paper/2610.01847/) (2026)

## Abstract (arXiv)

Companies that develop foundation models publish behavioral guidelines they pledge their models will follow, but it remains unclear if models actually do so. While providers such as OpenAI, Anthropic, and Google have published detailed specifications describing both desired safety constraints and qualitative traits for their models, there has been no systematic audit of adherence to these guidelines. We introduce an automated framework that audits models against their providers specifications by parsing behavioral statements, generating targeted prompts, and using models to judge adherence. Our central focus is on three way consistency between a provider specification, its model outputs, and its own models as judges; an extension of prior two way generator validator consistency. This establishes a necessary baseline: at minimum, a foundation model should consistently satisfy the developer behavioral specifications when judged by the developer evaluator models. We apply our framework to 16 models from six developers across more than 100 behavioral statements, finding systematic inconsistencies including compliance gaps of up to 20 percent across providers.