# SciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing

arXiv: https://arxiv.org/abs/2605.29468 · HTML: https://mlsanity.com/paper/2605.29468/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 7 of 7)

- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Towards End-to-End Automation of AI Research](https://mlsanity.com/paper/2606.15497/) (2026)
- [LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts](https://mlsanity.com/paper/2410.10700/) (2024)
- [FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning](https://mlsanity.com/paper/2505.08054/) (2025)
- [SoSBench: Benchmarking Safety Alignment on Six Scientific Domains](https://mlsanity.com/paper/2505.21605/) (2025)
- [No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models](https://mlsanity.com/paper/2509.08075/) (2025)
- [TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis](https://mlsanity.com/paper/2505.24672/) (2025)

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

- [Editorial routing shapes how computational results are qualified in AI-assisted scientific writing](https://mlsanity.com/paper/2609.14288/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used to support scientific work, but it is unclear whether they uphold responsible conduct of research (RCR) norms or help undermine them. We introduce SciIntBench, an adversarial benchmark of 810 prompts across ten RCR categories and three scientific domains. Each scenario appears as an Overt Adversarial, Covert Adversarial, and Benign version, allowing us to jointly measure framing-sensitive refusal of misconduct and helpfulness on legitimate requests. We evaluate 16 commercial and open-weight LLMs from six providers (2024--2026), producing 12,960 responses. We find that scientific integrity alignment is strongly framing-sensitive: models refuse explicit misconduct far more reliably than covert violations, especially failing when misconduct is presented as a pressure-driven shortcut. Refusals vary by RCR category, with weaker boundaries around transparency, plagiarism, and fabrication.