Human-AI Decision Making

Ask about this topic

Overview

The field examines how people and AI can combine judgment, divide tasks, or transfer decision authority, especially when decisions are uncertain or consequential. Common approaches include calibrated advice, selective prediction and deferral, adaptive routing and ensembles, preference elicitation, and explanations designed to support human review. Researchers test these methods in behavioral experiments and applied settings such as clinical diagnosis, finance, negotiation, and public services, measuring both decision outcomes and interaction behavior. A central tension is that AI assistance can improve performance yet also encourage overreliance, weaken human skills, or shift influence and responsibility; gains depend on task context, complementary strengths, and whether people can detect when the AI is wrong.

Latest papers

CardsList

175 papers22 papers in the last four weeks, up 5% on the four weeks before. 0.1% of all new papers.

Mar 11, 2026

Human-AI Co-reasoning for Clinical Diagnosis with Evidence-Integrated Language Agent

We present PULSE, a medical reasoning agent that combines a domain-tuned large language model with scientific literature retrieval to support diagnostic decision-making in complex real-world cases. To evaluate its capabilities, we curated a benchmark of 82 authentic endocrinology case reports encompassing a broad spectrum of disease types and incidence levels. In controlled experiments, we compared PULSE's performance against physicians with varying levels of expertise-from residents to senior specialists-and examined how AI assistance influenced human diagnostic reasoning. PULSE attained expert-competitive accuracy, outperforming residents and junior specialists while matching senior specialist performance at both Top@1 and Top@4 thresholds. Unlike physicians, whose accuracy declined with disease rarity, PULSE maintained stable performance across incidence tiers. The agent also exhibited adaptive reasoning, increasing output length with case difficulty in a manner analogous to the longer deliberation observed among expert clinicians. When used collaboratively, PULSE enabled physicians to correct initial errors and broaden diagnostic hypotheses, but also introduced risks of automation bias. The study explores both serial and concurrent collaboration workflows, revealing that PULSE offers robust support across common and rare presentations. These findings underscore both the promise and the limitations of language model-based agents in clinical diagnosis, and offer a framework for evaluating their role in real-world decision-making.

Zhongzhen Huang, Yan Ling, Hong Chen +7

Shanghai Jiao Tong University, Shanghai, China · Department of Endocrinology, Zhongshan Hospital, Fudan University, Shanghai, China · Department of Endocrinology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China +3

Medical DiagnosisClinical Decision SupportHuman-AI Decision MakingMedical LLMsClinical Language Model Evaluation
AskPDF
Mar 10, 2026

Noncooperative Human-AI Agent Dynamics

This paper investigates the dynamics of noncooperative interactions between artificial intelligence agents and human decision-makers in strategic environments. In particular, motivated by extensive literature in behavioral Economics, human agents are more faithfully modeled with respect to the state of the art using Prospect Theoretic preferences, while AI agents are modeled with standard expected utility maximization. Prospect Theory incorporates known cognitive heuristics employed by humans, including reference dependence and greater loss aversion relative to utility to relative gains. This paper runs different combinations of expected utility and prospect theoretic agents in a number of classic matrix games as well as examples specialized to tease out distinctions in strategic behavior with respect to preference functions, to explore the emergent behaviors from mixed population (human vs. AI) competition. Extensive numerical simulations are performed across AI, aware humans (those with full knowledge of the game structure and payoffs), and learning Prospect Agents (i.e., for AIs representing humans). A number of interesting observations and patterns show up, spanning barely distinguishable behavior, behavior corroborating Prospect preference anomalies in the theoretical literature, and unexpected surprises. Code can be found at https://github.com/dylanwaldner/noncooperative-human-AI.

Dylan Waldner, Vyacheslav Kungurtsev, Mitchelle Ashimosi

Prospect TheoryHuman-AI Decision MakingGame TheoryHuman Behavior SimulationDecision-Making under Uncertainty
AskPDF
Mar 9, 2026

Alignment-Process-Outcome: Rethinking How AIs and Humans Collaborate

In real-world collaboration, alignment, process structure, and outcome quality do not exhibit a simple linear or one-to-one correspondence: similar alignment may accompany either rapid convergence or extensive multi-branch exploration, and lead to different results. Existing accounts often isolate these dimensions or focus on specific participant types, limiting structural accounts of collaboration. We reconceptualize collaboration through two complementary lenses. The task lens models collaboration as trajectory evolution in a structured task space, revealing patterns such as advancement, branching, and backtracking. The intent lens examines how individual intents are expressed within shared contexts and enter situated decisions. Together, these lenses clarify the structural relationships among alignment, decision-making, and trajectory structure. Rather than reducing collaboration to outcome quality or treating alignment as the sole objective, we propose a unified dynamic view of the relationships among alignment, process, and outcome, and use it to re-examine collaboration structure across Human-Human, AI-AI, and Human-AI settings.

Haichang Li, Anjun Zhu, Arpit Narechania

George Mason University, Fairfax, Virginia, USA · Simon Fraser University, Burnaby, British Columbia, Canada · The Hong Kong University of Science and Technology, Hong Kong S.A.R., China

Human-AI CollaborationHuman-AI Decision MakingHuman-AI Agreement
AskPDF
Mar 6, 2026

Not Too Short, Not Too Long: How LLM Response Length Shapes People's Critical Thinking in Error Detection

Large language models (LLMs) have become common decision-support tools across educational and professional contexts, raising questions about how their outputs shape human critical thinking. Prior work suggests that the amount of AI assistance can influence cognitive engagement, yet little is known about how specific properties of LLM outputs (e.g., response length) impacts users' critical evaluation of information. In this study, we examine whether the length of LLM responses shapes users' accuracy in evaluating LLM-generated reasoning on critical thinking tasks, particularly in interaction with the correctness of the LLM's reasoning. To begin evaluating this, we conducted a within-subjects experiment with 24 participants who completed 15 modified Watson--Glaser critical thinking items, each accompanied by an LLM-generated explanation that varied in length and correctness. Mixed-effects logistic regression revealed a strong and statistically reliable effect of LLM output correctness on participant accuracy, with participants more likely to answer correctly when the LLM's explanation was correct. Response length appeared to moderated this effect: when the LLM output was incorrect, medium-length explanations were associated with higher participant accuracy than either shorter or longer explanations, whereas accuracy remained high across lengths when the LLM output was correct. Together, these findings suggest that response length alone may be insufficient to support critical thinking, and that how reasoning is presented-including a potential advantage of mid-length explanations under some conditions-points to design opportunities for LLM-based decision-support systems that emphasize transparent reasoning and calibrated expressions of certainty.

Natalie Friedman, Adelaide Nyanyo, Kevin Weatherwax +4

BTP Innovation, SAP, Palo Alto, CA, USA

Human-AI Decision MakingLLM Reasoning
AskPDF
Mar 5, 2026

Not All Trust is the Same: Effects of Decision Workflow and Explanations in Human-AI Decision Making

A central challenge in AI-assisted decision making is achieving warranted, well-calibrated trust. Both overtrust (accepting incorrect AI recommendations) and undertrust (rejecting correct advice) should be prevented. Prior studies differ in the design of the decision workflow - whether users see the AI suggestion immediately (1-step setup) or have to submit a first decision beforehand (2-step setup) -, and in how trust is measured - through self-reports or as behavioral trust, that is, reliance. We examined the effects and interactions of (a) the type of decision workflow, (b) the presence of explanations, and (c) users' domain knowledge and prior AI experience. We compared reported trust, reliance (agreement rate and switch rate), and overreliance. Results showed no evidence that a 2-step setup reduces overreliance. The decision workflow also did not directly affect self-reported trust, but there was a crossover interaction effect with domain knowledge and explanations, suggesting that the effects of explanations alone may not generalize across workflow setups. Finally, our findings confirm that reported trust and reliance behavior are distinct constructs that should be evaluated separately in AI-assisted decision making.

Laura Spillner, Rachel Ringe, Robert Porzel +1

Digital Media Lab, University of Bremen, Germany

AI-Assisted Decision MakingTrust in AIHuman-AI Decision MakingExplainability Evaluation
AskPDF
Mar 3, 2026

Delegation and Verification Under AI

As AI systems enter institutional workflows, workers must decide whether to delegate task execution to AI and how much effort to invest in verifying AI outputs, while institutions evaluate workers using outcome-based standards that may misalign with workers' private costs. We model delegation and verification as the solution to a rational worker's optimization problem, and define worker quality by evaluating an institution-centered utility (distinct from the worker's objective) at the resulting optimal action. We formally characterize optimal worker workflows and show that AI induces phase transitions, where arbitrarily small differences in verification ability lead to sharply different behaviors. As a result, AI can amplify workers with strong verification reliability while degrading institutional worker quality for others who rationally over-delegate and reduce oversight, even when baseline task success improves and no behavioral biases are present. These results identify a structural mechanism by which AI reshapes institutional worker quality and amplifies quality disparities between workers with different verification reliability.

Lingxiao Huang, Wenyang Xiao, Nisheeth K. Vishnoi

Nanjing University · Yale University

Human-in-the-Loop AIHuman-AI Decision MakingHuman Oversight of AIAI and Labor
AskPDF
Mar 2, 2026

Strategic Advice in the Age of Personal AI

Personal AI assistants are changing how individuals use advice. We study how an advisor should design its recommendation in anticipation of stochastic consultation with personal AI whose recommendation is predictable. Personal AI enters through two dimensions: consultation probability and relative trust, which captures the relative influence personal AI receives when consulted. In the baseline model, the advisor optimally counteracts the personal AI signal. Counteraction increases with consultation probability but is hump-shaped in relative trust. The advisor's minimized loss is hump-shaped in consultation probability, vanishing when personal AI is never or always consulted. Greater relative trust in personal AI increases the irreducible loss arising from stochastic consultation. We extend the analysis to partial predictability and costly recommendation adjustment, characterizing their effects on optimal recommendations and minimized loss. The framework also accommodates richer information structures, including settings in which personal AI is perceived as having access to private information relevant to the task. We introduce an online forecasting experiment that examines how participants obtain personal AI advice and combine it with an advisor's recommendation and their initial judgments. Participants place weight on all three inputs. When access requires an additional action, some participants do not seek personal AI advice, while some others attempt to obtain it without success. Together, these findings highlight two distinct aspects of personal AI use: whether advice is obtained and how much weight it receives when available.

Yueyang Liu, Wichinpong Park Sinchaisri

1Jones Graduate School of Business, Rice University · 2Haas School of Business, University of California, Berkeley

Trust in AIHuman-AI Decision MakingPersonal AI Agents
AskPDF
Feb 25, 2026

Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts

Large language models are increasingly used in decision-making tasks that require them to process information from a variety of sources, including both human experts and other algorithmic agents. How do LLMs weigh the information provided by these different sources? We consider the well-studied phenomenon of algorithm aversion, in which human decision-makers exhibit bias against predictions from algorithms. Drawing upon experimental paradigms from behavioural economics, we evaluate how eightdifferent LLMs delegate decision-making tasks when the delegatee is framed as a human expert or an algorithmic agent. To be inclusive of different evaluation formats, we conduct our study with two task presentations: stated preferences, modeled through direct queries about trust towards either agent, and revealed preferences, modeled through providing in-context examples of the performance of both agents. When prompted to rate the trustworthiness of human experts and algorithms across diverse tasks, LLMs give higher ratings to the human expert, which correlates with prior results from human respondents. However, when shown the performance of a human expert and an algorithm and asked to place an incentivized bet between the two, LLMs disproportionately choose the algorithm, even when it performs demonstrably worse. These discrepant results suggest that LLMs may encode inconsistent biases towards humans and algorithms, which need to be carefully considered when they are deployed in high-stakes scenarios. Furthermore, we discuss the sensitivity of LLMs to task presentation formats that should be broadly scrutinized in evaluation robustness for AI safety.

Jessica Y. Bo, Lillio Mok, Ashton Anderson

Computer Science University of Toronto

Human-AI Decision MakingLLM Decision-MakingLanguage Model Bias EvaluationAlgorithmic Bias
AskPDF
Feb 25, 2026

2-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support

Prognostic predictions from ML models support human decision making in several fields, including high-stakes ones such as healthcare and the judiciary. Yet, we still lack a clear understanding of how decision makers learn from ML-based decision support (ML-DS). In this paper, we introduce a general computational framework, the 2-Step Agent, to capture how a prediction from an ML model can also be used as a source of useful information about the training data and the causal mechanism that generated it. Our framework models (i) how a prediction from an ML model affects the beliefs of a rational Bayesian agent, and (ii) how this change in beliefs affects the estimation of the causal effect, the downstream decision for a new observation, and the subsequent outcome. In addition to the framework itself, we make three contributions. First, for the multivariate linear-Gaussian setting, we derive a tractable solution for the Bayesian inference problem introduced, i.e. one in which the agent infers information about a population from an ML prediction. Second, we experimentally identify conditions under which ML-DS is beneficial compared to unassisted decision making. Third, we show that a single misaligned prior belief of the user can be sufficient for ML-DS to lead to worse downstream outcomes compared to no decision support even when the prognostic model is well-specified and the agent is perfectly rational. Hence, even under ideal conditions, ML-DS can do more harm than good.

Otto Nyberg, Davide Tugnoli, Fausto Carcassi +1

Institute for Logic, Language and Computation, University of Amsterdam, the Netherlands · Department of Mathematics and Earth Sciences, University of Trieste, Italy

AI-Assisted Decision MakingHuman-AI Decision MakingBayesian Decision Theory
AskPDF
Feb 23, 2026

Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration

In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decreased AI performance in areas of human strengths. This can inadvertently erode human trust and cause them to ignore AI advice precisely when it is most needed. Conversely, an aligned AI fosters trust yet risks reinforcing suboptimal human behavior and lowering human-AI team performance. In this paper, we start by identifying this fundamental tension between performance-boosting (i.e., complementarity) and trust-building (i.e., alignment) as an inherent limitation of the traditional approach for training a single AI model to assist human decision making. To overcome this, we introduce a novel human-centered adaptive AI ensemble that strategically toggles between two specialist AI models - the aligned model and the complementary model - based on contextual cues, using an elegantly simple yet provably near-optimal Rational Routing Shortcut mechanism. Comprehensive theoretical analyses elucidate why the adaptive AI ensemble is effective and when it yields maximum benefits. Moreover, experiments on both simulated and real-world data show that when humans are assisted by the adaptive AI ensemble in decision making, they can achieve significantly higher performance than when they are assisted by single AI models that are trained to either optimize for their independent performance or even the human-AI team performance.

Hasan Amin, Ming Yin, Rajiv Khanna

Purdue University, USA

Human-AI ComplementarityHuman-AI CollaborationHuman-AI Decision MakingEnsemble Learning
AskPDF
Feb 19, 2026

Multi-Round Human-AI Collaboration with User-Specified Requirements

As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions reliably improve decision quality. We adopt a human centric view governed by two principles: counterfactual harm, ensuring the AI does not undermine human strengths, and complementarity, ensuring it adds value where the human is prone to err. We formalize these concepts via user defined rules, allowing users to specify exactly what harm and complementarity mean for their specific task. We then introduce an online, distribution free algorithm with finite sample guarantees that enforces the user-specified constraints over the collaboration dynamics. We evaluate our framework across two interactive settings: LLM simulated collaboration on a medical diagnostic task and a human crowdsourcing study on a pictorial reasoning task. We show that our online procedure maintains prescribed counterfactual harm and complementarity violation rates even under nonstationary interaction dynamics. Moreover, tightening or loosening these constraints produces predictable shifts in downstream human accuracy, confirming that the two principles serve as practical levers for steering multi-round collaboration toward better decision quality without the need to model or constrain human behavior.

Sima Noorani, Shayan Kiyani, Hamed Hassani +1

University of Pennsylvania

Human-AI ComplementarityHuman-AI CollaborationHuman-AI Decision MakingOnline Learning
AskPDF
Feb 19, 2026

The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions

Large Language Model-powered conversational agents (CAs) are increasingly capable of projecting sophisticated personalities through language, but how these projections affect users is unclear. We thus examine how CA personalities expressed linguistically affect user decisions and perceptions in the context of charitable giving. In a crowdsourced study, 360 participants interacted with one of eight CAs, each projecting a personality composed of three linguistic aspects: attitude (optimistic/pessimistic), authority (authoritative/submissive), and reasoning (emotional/rational). While the CA's composite personality did not affect participants' decisions, it did affect their perceptions and emotional responses. Particularly, participants interacting with pessimistic CAs felt lower emotional state and lower affinity towards the cause, perceived the CA as less trustworthy and less competent, and yet tended to donate more toward the charity. Perceptions of trust, competence, and situational empathy significantly predicted donation decisions. Our findings emphasize the risks CAs pose as instruments of manipulation, subtly influencing user perceptions and decisions.

Uğur Genç, Heng Gu, Chadha Degachi +3

Delft University of Technology, Delft, Netherlands

Persuasion in Language ModelsHuman-AI Decision MakingTrust in AI
AskPDF
Feb 18, 2026

Human-AI Collaboration in Large Language Model-Integrated Building Energy Management Systems: The Role of User Domain Knowledge and AI Literacy

This study aimed to comprehend how user domain knowledge and artificial intelligence (AI) literacy impact the effective use of human-AI interactive building energy management system (BEMS). While prior studies have investigated the potential of integrating large language models (LLMs) into BEMS or building energy modeling, very few studies have examined how user interact with such systems. We conducted a systematic role-playing experiment, where 85 human subjects interacted with an advanced generative pre-trained transformer (OpenAI GPT-4o). Participants were tasked with identifying the top five behavioral changes that could reduce home energy use with the GPT model that functioned as an LLM-integrated BEMS. Then, the collected prompt-response data and participant conclusions were analyzed using an analytical framework that hierarchically assessed and scored human-AI interactions and their home energy analysis approaches. Also, participants were classified into four groups based on their self-evaluated domain knowledge of building energy use and AI literacy, and Kruskal-Wallis H tests with post-hoc pairwise comparisons were conducted across 20 quantifiable metrics. Key takeaways include: most participants employed concise prompts (median: 16.2 words) and relied heavily on GPT's analytical capabilities; and notably, only 1 of 20 metrics, appliance identification rate, showed statistically significant group differences (p=0.037), driven by AI literacy rather than domain knowledge, suggesting an equalizing effect of LLMs across expertise levels. This study provides foundational insights into human-AI collaboration dynamics and promising development directions in the context of LLM-integrated BEMS and contributes to realizing human-centric LLM-integrated energy systems.

Wooyoung Jung, Kahyun Jeon, Prosper Babon-Ayeng

The University of Arizona · Illinois Institute of Technology

Human-AI CollaborationHuman-AI InteractionHuman-AI Decision MakingBuilding Energy Management
AskPDF
Feb 16, 2026

Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decision-making under uncertainty remains limited. We study LLM risky choices along two dimensions: (1) prospect representation (based on an explicit representation or outcome history) and (2) decision rationale (explanation). Our study, which involves 20 frontier and open LLMs, is complemented by a matched human subjects experiment, which provides one reference point, while an expected payoff maximizing rational agent model provides another. We find that LLMs cluster into two categories: reasoning models (RMs) and conversational models (CMs). RMs tend towards rational behavior, are insensitive to the order of prospects, gain/loss framing, and explanations, and behave similarly whether prospects are explicit or presented via a history of outcomes. CMs are significantly less rational, slightly more human-like, sensitive to prospect ordering, framing, and explanation, and exhibit a large description-history gap. Paired comparisons of open LLMs suggest that a key factor differentiating RMs and CMs is training for mathematical reasoning.

Luise Ge, Yongyan Zhang, Yevgeniy Vorobeychik

Washington University in St. Louis

LLM Decision-MakingFraming Effects in Language ModelsLarge Reasoning ModelsHuman-AI Decision Making
AskPDF
Feb 12, 2026

Choose Your Agent: Tradeoffs in Adopting AI Advisors, Coaches, and Delegates in Multi-Party Negotiation

As AI usage becomes more prevalent in social contexts, understanding agent-user interaction is critical to designing systems that imp rove both individual and group outcomes. We present an online behavioral experiment (N=243) in which participants play three multi-tu rn bargaining games in groups of three. Each game, presented in randomized order, grants access to a single LLM assistance modality: proactive recommendations from an Advisor, reactive feedback from a Coach, or autonomous execution by a Delegate. All three modalitie s are powered by an LLM with super-human performance within this negotiation setting. On each turn, participants privately decide whe ther to act manually or use the AI modality available in that game. We document a preference-performance misalignment: participants s trongly prefer the higher-control Advisor (44%) over the Delegate (19%), yet groups only significantly increase collective surplus un der Delegate access. Adjusting for voluntary non-compliance, delegating to the AI yields suggestive individual welfare gains, roughly 1.5x the intent-to-treat estimate. A mechanism analysis traces this gap to a human filter: AI-generated proposals create more joint surplus than manual proposals across all conditions, but in the Advisor and Coach modes users modify, override, or ignore the AI's su ggestions, reverting toward human-baseline trade patterns. The Delegate advantage arises not from a different AI capability but from bypassing this filtering step altogether. Realizing these welfare gains depends not only on model capability, but on the interaction structure through which that capability is delivered. We argue that assistance modalities should be designed as mechanisms with endog enous participation; adoption-compatible interaction rules are a prerequisite to improving welfare with automated assistance.

Kehang Zhu, Nithum Thain, Vivian Tsai +2

Harvard University, United States · Google DeepMind, Canada · Google DeepMind, United States +1

Automated NegotiationHuman-AI InteractionHuman-AI Decision MakingHuman-AI Collaboration
AskPDF
Feb 12, 2026

Using predictive multiplicity to measure individual performance within the AI Act

When building AI systems for decision support, one often encounters the phenomenon of predictive multiplicity: a single best model does not exist; instead, one can construct many models with similar overall accuracy that differ in their predictions for individual cases. Especially when decisions have a direct impact on humans, this can be highly unsatisfactory. For a person subject to high disagreement between models, one could as well have chosen a different model of similar overall accuracy that would have decided the person's case differently. We argue that this arbitrariness conflicts with the EU AI Act, which requires providers of high-risk AI systems to report performance not only at the dataset level but also for specific persons. The goal of this paper is to put predictive multiplicity in context with the EU AI Act's provisions on accuracy and to subsequently derive concrete suggestions on how to evaluate and report predictive multiplicity in practice. Specifically: (1) We introduce the AI Act's accuracy provisions and argue that incorporating information about predictive multiplicity could serve compliance with specific provisions for providers. (2) Based on this legally rigorous analysis, we suggest individual conflict ratios and δδ-ambiguity as tools to quantify the disagreement between models on individual cases and to help detect individuals subject to conflicting predictions. (3) Based on computational insights, we derive easy-to-implement rules on how model providers could evaluate predictive multiplicity in practice. (4) Ultimately, we suggest that information about predictive multiplicity should be made available to deployers under the AI Act, enabling them to judge whether system outputs for specific individuals are reliable enough for their use case.

Karolin Frohnapfel, Mara Seyfert, Sebastian Bordt +2

University of Tübingen and Tübingen AI Center, Germany · Tübingen AI Center, Germany · University of Tübingen and CZS Institute for Artificial Intelligence and Law, Germany +2

AI AccountabilityAI GovernanceHuman-AI Decision Making
AskPDF
Feb 6, 2026

Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task

Whether in agentic workflows, social studies, or chat settings, large language models (LLMs) are increasingly being asked to replace humans in choosing which goals to pursue, rather than completing predefined tasks. However, the assumption that LLMs accurately reflect human preferences for goal setting remains largely untested. We assess the validity of LLMs as proxies for human goal selection in a controlled, self-directed learning task borrowed from cognitive science. Across five models (GPT-5, Gemini 2.5 Pro, Claude Sonnet 4.5, Qwen3 32B, and Centaur), we find substantial divergence from human behavior. While people gradually explore and learn to achieve goals with diversity across individuals, most models exploit a single identified solution or show surprisingly low performance, with distinct patterns across models and little variability across instances of the same model. Chain-of-thought reasoning and persona steering provide limited improvements, and our conclusions hold across experimental settings. While they await confirmation in applied settings, these findings highlight the uniqueness of human goal selection and caution against its replacement with current models.

Gaia Molinaro, Dave August, Danielle Perszyk +1

University of California, Berkeley · Amazon AGI Lab

Human-AI Decision Making
AskPDF
Jan 16, 2026

Predicting Biased Human Decision-Making with Large Language Models in Conversational Settings

We examine whether large language models (LLMs) can predict biased decision-making in conversational settings, and whether their predictions capture not only human cognitive biases but also how those effects change under cognitive load. In a pre-registered study (N = 1,648), participants completed six classic decision-making tasks via a chatbot with dialogues of varying complexity. Participants exhibited two well-documented cognitive biases: the Framing Effect and the Status Quo Bias. Increased dialogue complexity resulted in participants reporting higher mental demand. This increase in cognitive load selectively, but significantly, increased the effect of the biases, demonstrating the load-bias interaction. We then evaluated whether LLMs (GPT-4, GPT-5, and open-source models) could predict individual decisions given demographic information and prior dialogue. While results were mixed across choice problems, LLM predictions that incorporated dialogue context were significantly more accurate in several key scenarios. Importantly, their predictions reproduced the same bias patterns and load-bias interactions observed in humans. Across all models tested, the GPT-4 family consistently aligned with human behavior, outperforming GPT-5 and open-source models in both predictive accuracy and fidelity to human-like bias patterns. These findings advance our understanding of LLMs as tools for simulating human decision-making and inform the design of conversational agents that adapt to user biases.

Stephen Pilli, Vivek Nallur

University College Dublin · Dublin, Ireland

LLM Decision-MakingHuman-AI Decision Making
AskPDF
Dec 12, 2025

Generative AI for Analysts

We study how generative artificial intelligence (GenAI) reshapes financial analysts' information production. Using the 2023 integration of GenAI into FACTSET as a plausibly exogenous change in AI access, we find that FACTSET-associated reports become markedly richer--featuring 26% more distinct information sources, 24% broader topical coverage, and 21% more analytical methods--while also improving timeliness. However, these gains do not uniformly improve decision quality: relative forecast accuracy declines when analysts face greater information-processing demands. Yet, a machine-learning benchmark processing the same observable inputs shows no analogous deterioration, pointing to a human processing constraint rather than poorer underlying information. Placebo tests using other data vendors make a common platform-wide technology trend unlikely. Overall, GenAI relaxes information-acquisition constraints while making human attention a more important bottleneck.

Jian Xue, Qian Zhang, Wu Zhu

School of Economics and Management, Tsinghua University · School of Management, Xiamen University

Financial ServicesFinancial ForecastingHuman-AI Decision MakingFinance
AskPDF
Sep 26, 2025

It's My Agent, Not Me: Personal Privacy Boundaries in AI-Delegated Information Sharing

Aligning AI systems with human privacy preferences requires understanding individuals' nuanced disclosure behaviors beyond general privacy norms. Yet eliciting these boundaries remains challenging because they involve context-dependent trade-offs. We present an elicitation approach that probes individuals' privacy boundaries through a discriminative task. Through a between-subjects study with varying communication roles and delegation conditions, we collected 1,650 privacy boundaries from 169 participants across 60 scenarios. We examined how communication roles, AI delegation, and individual differences influence boundaries. Results show that communication roles significantly influence sensitivity to disclosure granularity or identifiability, depending on whose private information is shared; AI delegation and individuals' need for privacy heighten sensitivity to disclosed identifiers. Our analysis further reveals how AI delegation shifts privacy preferences across contexts, highlighting new complexities in AI-mediated communication. We advocate eliciting nuanced privacy boundaries within real-world data flows by considering roles and AI delegation, and enabling user involvement in guiding privacy-aware AI behavior.

Bingcan Guo, Eryue Xu, Zhiping Zhang +1

Department of Human Centered Design & Engineering, University of Washington, United States · School of Information Sciences, University of Illinois Urbana-Champaign, United States · Khoury College of Computer Sciences, Northeastern University, United States

Preference ElicitationHuman-AI Decision Making
AskPDF
Sep 25, 2025

Understanding Role Switching in Human-AI Collaboration through Multimodal Behavioral Signals

Human-AI collaboration often requires dividing complex tasks into complementary subtasks. As a task unfolds, users may want to shift which subtasks they perform and which their AI partner performs, in response to evolving task demands and perceptions of the AI's capabilities. In this work, we investigate whether behavioral signals can reveal such changes during a sequential decision-making task. We conducted a study using hand-and-brain chess, where, on each turn, participants chose either to select the piece type (brain) while their AI partner chose the move (hand), or to choose the move after the AI selected the piece type. Across 21 chess players, this yielded more than 1,100 decisions to retain their role from the previous turn or switch to the other role. Players generally retained their current roles across turns. When participants did switch, they exhibited more exploratory gaze patterns and role switches were associated with lower subsequent move quality. Using these behavioral and task-specific signals, we trained a classifier to distinguish switch from stay decisions, achieving a PR-AUC of 0.56 (compared to a random baseline of 0.39). Feature-set ablations showed that gaze and task-specific features contributed most to model performance. Role switching was not a simple choice between controlling and delegating the task as both roles required participants to perform one subtask and delegate the other. However, interviews showed that many participants perceived selecting the piece type as giving them greater control. Perceived AI ability, relative subtask difficulty, and desired influence over the direction of play shaped these role preferences. These findings suggest that behavioral cues could help intelligent systems recognize when users want to reallocate complementary responsibilities during collaboration.

Avinash Ajit Nargund, Arthur Caetano, Kevin Yang +7

University of California, Santa Barbara, USA · Washington University in St.Louis, USA

Intent ClassificationHuman-AI Decision MakingHuman-AI Collaboration
AskPDF
Aug 11, 2025

Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI

Uncertainty in artificial intelligence (AI) predictions raises pressing legal and ethical questions for AI-assisted decision-making. This article examines two uncertainty-based algorithmic interventions that act as guardrails for human-AI interaction: selective abstention, which withholds high-uncertainty predictions from human decision-makers, and selective friction, which presents such predictions together with salient warnings about the model's uncertainty. Prior work suggests that uncertainty-based abstention can exacerbate disparities where under-represented groups are more likely to receive uncertain predictions. We provide, to our knowledge, the first doctrinal analysis of uncertainty-based algorithmic interventions under laws from the United Kingdom and examine their consequences through two AI-assisted case studies: consumer credit and risk of reoffending. We show that the use of uncertainty thresholds, though formally neutral, can generate discriminatory effects. We argue that both interventions pose risks of unlawful discrimination, but that selective friction is legally preferable. It preserves access to the prediction and is more likely to satisfy proportionality under the Equality Act 2010. Whether selective friction also improves decision quality in practice is uncertain. We identify conditions under which it may improve or worsen decision quality.

Holli Sargeant, Mackenzie Jorgensen, Arina Shah +3

University of Cambridge, United Kingdom · Northumbria University, Newcastle, United Kingdom · George Washington University, Washington D.C., United States +2

Selective PredictionAlgorithmic FairnessAlgorithmic BiasHuman-AI Decision Making
AskPDF
Jul 1, 2025

Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Conversational Group Decision Support

More than twenty-five years ago, early ideas emerged on how to design systems that provide recommendations to groups of users rather than individuals. Since then, a wide range of algorithmic approaches has been proposed to elicit individual preferences, aggregate them, and generate group recommendations. However, despite this substantial body of work, relatively few examples of real-world group recommender systems are in use. This observation invites reflection on the assumptions of the academic research, particularly regarding how inter-group communication unfolds and how recommendation-supported decisions should be made. In this essay, we suggest that some of these assumptions and corresponding system designs may not fully align with users' needs or expectations. We therefore outline a forward-looking perspective that explores how insights from group-decision making research and recent advances in Generative AI, including systems such as ChatGPT, could better inform the design of group recommender systems. As one possible direction, we consider settings in which human group members interact and exchange information through a chat based interface, while an AI-based agent supports the decision-making process. Such an approach may contribute to design more natural group and system interactions, and could help facilitate a broader adoption of group recommender systems in practice.

Dietmar Jannach, Amra Delić, Francesco Ricci +1

University of Klagenfurt, Austria · University of Sarajevo, Bosnia · Free University of Bozen-Bolzano, Italy

Recommender SystemsHuman-AI Decision Making
AskPDF
May 22, 2025

Serious Games: Human-AI Interaction, Evolution, and Coevolution

The serious games between humans and AI have only just begun. Evolutionary Game Theory (EGT) models the competitive and cooperative strategies of biological entities. EGT could help predict the potential evolutionary equilibrium of humans and AI. The objective of this work was to examine EGT models relevant to human-AI interaction, evolution, and co-evolution. Of thirteen EGT models considered, three were examined: the Hawk-Dove Game, Iterated Prisoner's Dilemma, and the War of Attrition. This selection was based on the widespread acceptance and clear relevance of these models to potential human-AI evolutionary dynamics and co-evolutionary trajectories. The Hawk-Dove Game predicts balanced mixed-strategy equilibria based on the costs of conflict. Iterated Prisoner's Dilemma suggests that repeated interaction may lead to cognitive co-evolution. The War of Attrition suggests that competition for resources may result in strategic co-evolution, asymmetric equilibria, and conventions on sharing resources. Each model was examined from the perspective of human and AI decision-making, from psychological and biological perspectives, and from an AI viewpoint. AI is being shaped by human input and is evolving in response to it. So too, neuroplasticity allows the human brain to evolve in response to stimuli. If humans and AI converge in future, what might be the result of human neuroplasticity combined with an ever-evolving AI? There are profound ethical and cognitive implications. EGT may provide a suitable framework to understand and predict human-AI interaction, evolution, and co-evolution. However, future research should extend beyond EGT and explore additional frameworks, empirical validation methods, and interdisciplinary perspectives. In the spirit of further exploration, an illustrative computational simulation is provided.

Nandini Doreswamy, Louise Horstmanshof

Southern Cross University, Lismore, New South Wales, Australia · National Coalition of Independent Scholars · National Coalition of Independent Scholars (NCIS)

Human-AI InteractionHuman-AI Decision MakingEvolutionary Game Theory
AskPDF
Jan 30, 2024

Human Responses to Algorithmic Correction: Evidence from Centre Court

We study how algorithmic review changes the initial decisions that a system is designed to correct. Using Hawk-Eye data from professional tennis, we compare umpire decisions with and without review against a common accuracy benchmark. Under review, initial errors were 8.6 percentage points higher just outside the line and lower for comparably close balls inside. We find no evidence that average initial accuracy deteriorated. Within matches, reversals were followed by larger adjustments than upheld calls, consistent with adaptation to correction. Overall, correction offsets worse initial decisions for incorrect in calls and reinforces better initial decisions for incorrect out calls. Whether review lowers organizational costs depends jointly on these changes and the costs of remedying corrected errors. A conditional illustration shows how utilization spreads fixed review costs across calls.

David Almog, Romain Gauriot, Lionel Page +1

Kellogg School of Management, Northwestern University · Deakin University · University of Queensland +1

Human-AI Decision MakingHuman Oversight of AIAI-Assisted Decision Making
AskPDF