Beyond static AI evaluations: advancing human interaction evaluations for LLM harms and risks
Ibrahim, Lujain, Huang, Saffron, Ahmad, Lama, Anderljung, Markus
–arXiv.org Artificial Intelligence
Model evaluations are central to understanding the safety, risks, and societal impacts of AI systems. While most real-world AI applications involve human-AI interaction, most current evaluations (e.g., common benchmarks) of AI models do not. Instead, they incorporate human factors in limited ways, assessing the safety of models in isolation, thereby falling short of capturing the complexity of human-model interactions. In this paper, we discuss and operationalize a definition of an emerging category of evaluations -- "human interaction evaluations" (HIEs) -- which focus on the assessment of human-model interactions or the process and the outcomes of humans using models. First, we argue that HIEs can be used to increase the validity of safety evaluations, assess direct human impact and interaction-specific harms, and guide future assessments of models' societal impact. Second, we propose a safety-focused HIE design framework -- containing a human-LLM interaction taxonomy -- with three stages: (1) identifying the risk or harm area, (2) characterizing the use context, and (3) choosing the evaluation parameters. Third, we apply our framework to two potential evaluations for overreliance and persuasion risks. Finally, we conclude with tangible recommendations for addressing concerns over costs, replicability, and unrepresentativeness of HIEs.
arXiv.org Artificial Intelligence
Jul-12-2024
- Country:
- North America > United States
- New York > New York County
- New York City (0.04)
- California
- San Francisco County > San Francisco (0.04)
- Los Angeles County > Santa Monica (0.04)
- New York > New York County
- Europe > United Kingdom
- England > Oxfordshire > Oxford (0.04)
- Asia > Middle East
- Jordan (0.04)
- Africa > Eswatini
- North America > United States
- Genre:
- Research Report
- Experimental Study (1.00)
- Strength High (0.68)
- Research Report
- Industry:
- Information Technology > Security & Privacy (0.68)
- Government > Regional Government (0.68)
- Health & Medicine
- Therapeutic Area (0.68)
- Pharmaceuticals & Biotechnology (0.46)
- Technology: