Chat-based prompts respond with verbose linear-sequential texts, making it difficult to explore and refine ambiguous intents, back up and reinterpret, or shift directions in creative AI-assisted design work. AI-Instruments instead embody "prompts" as interface objects via three key principles: (1) Reification of user-intent as reusable direct-manipulation instruments; (2) Reflection of multiple interpretations of ambiguous user-intents (Reflection-in-intent) as well as the range of AI-model responses (Reflection-in-response) to inform design "moves" towards a desired result; and (3) Grounding to instantiate an instrument from an example, result, or extrapolation directly from another instrument. Further, AI-Instruments leverage LLM's to suggest, vary, and refine new instruments, enabling a system that goes beyond hard-coded functionality by generating its own instrumental controls from content. We demonstrate four technology probes, applied to image generation, and qualitative insights from twelve participants, showing how AI-Instruments address challenges of intent formulation, steering via direct manipulation, and non-linear iterative workflows to reflect and resolve ambiguous intents.

Large generative models (LMs) are increasingly being considered for high-stakes decision-making. This work considers how such models compare to humans and predictive AI models on a specific case of recidivism prediction. We combine three datasets -- COMPAS predictive AI risk scores, human recidivism judgements, and photos -- into a dataset on which we study the properties of several state-of-the-art, multimodal LMs. Beyond accuracy and bias, we focus on studying human-LM alignment on the task of recidivism prediction. We investigate if these models can be steered towards human decisions, the impact of adding photos, and whether anti-discimination prompting is effective. We find that LMs can be steered to outperform humans and COMPAS using in context-learning. We find anti-discrimination prompting to have unintended effects, causing some models to inhibit themselves and significantly reduce their number of positive predictions.

Human-AI collaboration for decision-making strives to achieve team performance that exceeds the performance of humans or AI alone. However, many factors can impact success of Human-AI teams, including a user's domain expertise, mental models of an AI system, trust in recommendations, and more. This work examines users' interaction with three simulated algorithmic models, all with similar accuracy but different tuning on their true positive and true negative rates. Our study examined user performance in a non-trivial blood vessel labeling task where participants indicated whether a given blood vessel was flowing or stalled. Our results show that while recommendations from an AI-Assistant can aid user decision making, factors such as users' baseline performance relative to the AI and complementary tuning of AI error types significantly impact overall team performance. Novice users improved, but not to the accuracy level of the AI. Highly proficient users were generally able to discern when they should follow the AI recommendation and typically maintained or improved their performance. Mid-performers, who had a similar level of accuracy to the AI, were most variable in terms of whether the AI recommendations helped or hurt their performance. In addition, we found that users' perception of the AI's performance relative on their own also had a significant impact on whether their accuracy improved when given AI recommendations. This work provides insights on the complexity of factors related to Human-AI collaboration and provides recommendations on how to develop human-centered AI algorithms to complement users in decision-making tasks.

What Y ou See Is What Y ou Get? Abstract Although systematic biases in decision-making are widely documented, the ways in which they emerge from different sources is less understood. We present a controlled experimental platform to study gender bias in hiring by decoupling the effect of world distribution (the gender breakdown of candidates in a specific profession) from bias in human decision-making. We explore the effectiveness of representation criteria, fixed proportional display of candidates, as an intervention strategy for mitigation of gender bias by conducting experiments measuring human decision-makers' rankings for who they would recommend as potential hires. Experiments across professions with varying gender proportions show that balancing gender representation in candidate slates can correct biases for some professions where the world distribution is skewed, although doing so has no impact on other professions where human persistent preferences are at play. We show that the gender of the decision-maker, complexity of the decision-making task and over-and under-representation of genders in the candidate slate can all impact the final decision. By decoupling sources of bias, we can better isolate strategies for bias mitigation in human-in-the-loop systems. Introduction Machine learning can aid decision-making and is used in recommendation systems that play increasingly prevalent roles in the world. We now deploy systems to help hire candidates (HireVue 2018), determine who to police more (V eale, V an Kleek, and Binns 2018), and assess the likelihood of an individual to recidivate on a crime (Angwin et al. 2016). Because these systems are trained on real world data, they often produce biased decision outcomes in a manner that is discriminatory against underrepresented groups. Systems have been found to unfairly discriminate against defendants of color in assessing bail (Angwin et al. 2016), incorrectly classify minority groups in facial recognition tasks (Raji and Buolamwini 2019), and engage in wage theft for honest workers (McInnis et al. 2016). While much of the algorithmic fairness literature has focused on understanding bias from algorithms in isolation (Dwork and Ilvento 2018),Copyright c null 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org). A biased decision can be impacted by world, algorithmic, and human bias.

When might human input help (or not) when assessing risk in fairness-related domains? Dressel and Farid asked Mechanical Turk workers to evaluate a subset of individuals in the ProPublica COMPAS data set for risk of recidivism, and concluded that COMPAS predictions were no more accurate or fair than predictions made by humans. We delve deeper into this claim in this paper. We construct a Human Risk Score based on the predictions made by multiple Mechanical Turk workers on the same individual, study the agreement and disagreement between COMPAS and Human Scores on subgroups of individuals, and construct hybrid Human+AI models to predict recidivism. Our key finding is that on this data set, human and COMPAS decision making differed, but not in ways that could be leveraged to significantly improve ground truth prediction. We present the results of our analyses and suggestions for how machine and human input may have complementary strengths to address challenges in the fairness domain.