# DarkPatterns-LLM: A Multi-Layer Benchmark for Detecting Manipulative and Harmful AI Behavior

arXiv: https://arxiv.org/abs/2512.22470 · HTML: https://mlsanity.com/paper/2512.22470/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 27 Dec 2025.

## Builds on (most cited first, 12 of 12)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [SafetyBench: Evaluating the Safety of Large Language Models](https://mlsanity.com/paper/2309.07045/) (2023)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [End User Accounts of Dark Patterns as Felt Manipulation](https://mlsanity.com/paper/2010.11046/) (2020)

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

- [CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model](https://mlsanity.com/paper/2606.06099/) (2026)

## Abstract (arXiv)

The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary labels and fail to capture the nuanced psychological and social mechanisms constituting manipulation. We introduce DarkPatterns-LLM, a comprehensive benchmark dataset and diagnostic framework for fine-grained assessment of manipulative content in LLM outputs across seven harm categories: Legal/Power, Psychological, Emotional, Physical, Autonomy, Economic, and Societal Harm. Our framework implements a four-layer analytical pipeline comprising Multi-Granular Detection (MGD), Multi-Scale Intent Analysis (MSIAN), Threat Harmonization Protocol (THP), and Deep Contextual Risk Alignment (DCRA). The dataset contains 401 meticulously curated examples with instruction-response pairs and expert annotations. Through evaluation of state-of-the-art models including GPT-4, Claude 3.5, and LLaMA-3-70B, we observe significant performance disparities (65.2%--89.7%) and consistent weaknesses in detecting autonomy-undermining patterns. DarkPatterns-LLM establishes the first standardized, multi-dimensional benchmark for manipulation detection in LLMs, offering actionable diagnostics toward more trustworthy AI systems.