# Towards interactive evaluations for interaction harms in human-AI systems

arXiv: https://arxiv.org/abs/2405.10632 · HTML: https://mlsanity.com/paper/2405.10632/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 68 references that are in the map.
- First posted on arXiv 17 May 2024.

## Builds on (most cited first, 30 of 30)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [Beyond Memorization: Violating Privacy Via Inference with Large Language Models](https://mlsanity.com/paper/2310.07298/) (2023)
- [Sociotechnical Safety Evaluation of Generative AI Systems](https://mlsanity.com/paper/2310.11986/) (2023)
- [Large language models that replace human participants can harmfully misportray and flatten identity groups](https://mlsanity.com/paper/2402.01908/) (2024)
- [Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction](https://mlsanity.com/paper/2210.05791/) (2022)
- [Evaluating Frontier Models for Dangerous Capabilities](https://mlsanity.com/paper/2403.13793/) (2024)
- [Evaluating Human-Language Model Interaction](https://mlsanity.com/paper/2212.09746/) (2022)
- [The Fallacy of AI Functionality](https://mlsanity.com/paper/2206.09511/) (2022)
- [On Measures of Biases and Harms in NLP](https://mlsanity.com/paper/2108.03362/) (2021)
- [SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety](https://mlsanity.com/paper/2404.05399/) (2024)
- [Evaluating Language Models for Mathematics through Interactions](https://mlsanity.com/paper/2306.01694/) (2023)
- ["It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents](https://mlsanity.com/paper/2309.11653/) (2023)
- [Rethinking Model Evaluation as Narrowing the Socio-Technical Gap](https://mlsanity.com/paper/2306.03100/) (2023)
- [Designing for Responsible Trust in AI Systems: A Communication Perspective](https://mlsanity.com/paper/2204.13828/) (2022)
- [The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions](https://mlsanity.com/paper/2310.12418/) (2023)
- [A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration](https://mlsanity.com/paper/2404.00405/) (2024)
- [The illusion of artificial inclusion](https://mlsanity.com/paper/2401.08572/) (2024)
- [The System Model and the User Model: Exploring AI Dashboard Design](https://mlsanity.com/paper/2305.02469/) (2023)
- [Characterizing and modeling harms from interactions with design patterns in AI interfaces](https://mlsanity.com/paper/2404.11370/) (2024)
- [Should agentic conversational AI change how we think about ethics? Characterising an interactional ethics centred on respect](https://mlsanity.com/paper/2401.09082/) (2024)
- [Human participants in AI research: Ethics and transparency in practice](https://mlsanity.com/paper/2311.01254/) (2023)
- [Common Metrics to Benchmark Human-Machine Teams (HMT): A Review](https://mlsanity.com/paper/2008.04855/) (2020)

## Built on by (most cited first, 29 of 29)

- [OpenAI's Approach to External Red Teaming for AI Models and Systems](https://mlsanity.com/paper/2503.16431/) (2025)
- [LearnLM: Improving Gemini for Learning](https://mlsanity.com/paper/2412.16429/) (2024)
- [AutoPenBench: Benchmarking Generative Agents for Penetration Testing](https://mlsanity.com/paper/2410.03225/) (2024)
- [What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct](https://mlsanity.com/paper/2605.21778/) (2026)
- [VeriLA: A Human-Centered Evaluation Framework for Interpretable Verification of LLM Agent Failures](https://mlsanity.com/paper/2503.12651/) (2025)
- [Measuring and mitigating overreliance to build human-compatible AI](https://mlsanity.com/paper/2509.08010/) (2025)
- [Evidence of a log scaling law for political persuasion with large language models](https://mlsanity.com/paper/2406.14508/) (2024)
- [KidLM: Advancing Language Models for Children -- Early Insights and Future Directions](https://mlsanity.com/paper/2410.03884/) (2024)
- [Computational Hermeneutics: Evaluating generative AI as a cultural technology](https://mlsanity.com/paper/2604.16403/) (2026)
- [AIReg-Bench: Benchmarking Language Models That Assess AI Regulation Compliance](https://mlsanity.com/paper/2510.01474/) (2025)
- [ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents](https://mlsanity.com/paper/2605.20251/) (2026)
- [Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation](https://mlsanity.com/paper/2411.12820/) (2024)
- [Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias](https://mlsanity.com/paper/2601.18486/) (2026)
- [Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift](https://mlsanity.com/paper/2603.26676/) (2026)
- [Interactive Evaluation Requires a Design Science](https://mlsanity.com/paper/2605.17829/) (2026)
- [ArGen: Auto-Regulation of Generative AI via GRPO and Policy-as-Code](https://mlsanity.com/paper/2509.07006/) (2025)
- [When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making](https://mlsanity.com/paper/2602.04003/) (2026)
- [Reflections and New Directions for Human-Centered Large Language Models](https://mlsanity.com/paper/2605.06901/) (2026)
- [What Makes an Evaluation Useful? Common Pitfalls and Best Practices](https://mlsanity.com/paper/2503.23424/) (2025)
- [Measuring Biological Capabilities and Risks of AI Agents](https://mlsanity.com/paper/2606.19899/) (2026)
- [Optimising for Flourishing: Flourishing Metrics and Return on Flourishing as Success Criteria for Artificial Intelligence and Post-AGI Economic Systems](https://mlsanity.com/paper/2608.00151/) (2026)
- [KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn](https://mlsanity.com/paper/2608.17150/) (2026)
- [RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies](https://mlsanity.com/paper/2603.11001/) (2026)
- [Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker's Dilemma](https://mlsanity.com/paper/2603.13294/) (2026)
- [Evaluating Epistemic Guardrails in AI Reading Assistants: A Behavioral Audit of a Minimal Prototype](https://mlsanity.com/paper/2604.27275/) (2026)
- [Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research](https://mlsanity.com/paper/2606.12247/) (2026)
- [Design Theater: Evaluating the Gap Between User-Facing Design Reasoning and Implementation in Generative UI Tools](https://mlsanity.com/paper/2607.22928/) (2026)
- [When Agents Act Unwatched: The Reduced-Supervision Paradox in Agentic AI](https://mlsanity.com/paper/2609.29547/) (2026)
- [CuBEs: Culturally-Situated Behavioral Evaluations and the Limitations of Culture-Blind LLM Judges](https://mlsanity.com/paper/2610.02622/) (2026)

## Abstract (arXiv)

Current AI evaluation methods, which rely on static, model-only tests, fail to account for harms that emerge through sustained human-AI interaction. As AI systems proliferate and are increasingly integrated into real-world applications, this disconnect between evaluation approaches and actual usage becomes more significant. In this paper, we propose a shift towards evaluation based on textitinteractional ethics, which focuses on textitinteraction harms - issues like inappropriate parasocial relationships, social manipulation, and cognitive overreliance that develop over time through repeated interaction, rather than through isolated outputs. First, we discuss the limitations of current evaluation methods, which (1) are static, (2) assume a universal user experience, and (3) have limited construct validity. Drawing on research from human-computer interaction, natural language processing, and the social sciences, we present practical principles for designing interactive evaluations. These include ecologically valid interaction scenarios, human impact metrics, and diverse human participation approaches. Finally, we explore implementation challenges and open research questions for researchers, practitioners, and regulators aiming to integrate interactive evaluations into AI governance frameworks. This work lays the groundwork for developing more effective evaluation methods that better capture the complex dynamics between humans and AI systems.