More Like this

1. Reasoning about knowledge in lie production

   https://doi.org/10.31234/osf.io/4mu8v  

   Tan, Zhi Yi; Jara-Ettinger, Julian; Berke, Marlene (May 2024, Proceedings of the Annual Meeting of the Cognitive Science Society)

   Theory of Mind enables us to represent and reason about other people's mental states like beliefs and knowledge. By considering what other people know, this allows us to strategically construct believable lies. Previous work has shown that people construct lies to be consistent with others' beliefs even when those beliefs differ from their own. However, in most real world cases, we don't know everything that the other person knows. We propose that to produce believable lies, the sender considers what private information the receiver may have. Here, we develop our theory into a computational model and test it in a novel paradigm that allows us to distinguish between knowledge shared between the lie sender and receiver and knowledge private to the receiver. Our main model successfully captures how people lie in this paradigm over alternative models. Overall, our work furthers our understanding of human social cognition in adversarial situations. 

   more » « less
2. Perceptions of Linguistic Uncertainty by Language Models and Humans

   https://doi.org/10.18653/v1/2024.emnlp-main.483  

   Belém, Catarina G; Kelly, Markelle; Steyvers, Mark; Singh, Sameer; Smyth, Padhraic (January 2024, Association for Computational Linguistics)

   *Uncertainty expressions* such as ‘probably’ or ‘highly unlikely’ are pervasive in human language. While prior work has established that there is population-level agreement in terms of how humans quantitatively interpret these expressions, there has been little inquiry into the abilities of language models in the same context. In this paper, we investigate how language models map linguistic expressions of uncertainty to numerical responses. Our approach assesses whether language models can employ theory of mind in this setting: understanding the uncertainty of another agent about a particular statement, independently of the model’s own certainty about that statement. We find that 7 out of 10 models are able to map uncertainty expressions to probabilistic responses in a human-like manner. However, we observe systematically different behavior depending on whether a statement is actually true or false. This sensitivity indicates that language models are substantially more susceptible to bias based on their prior knowledge (as compared to humans). These findings raise important questions and have broad implications for human-AI and AI-AI communication. 

   more » « less
3. Modeling Human Trust and Reliance in AI-Assisted Decision Making: A Markovian Approach

   https://doi.org/10.1609/aaai.v37i5.25748  

   Li, Zhuoyan; Lu, Zhuoran; Yin, Ming (June 2023, Proceedings of the AAAI Conference on Artificial Intelligence)

   The increased integration of artificial intelligence (AI) technologies in human workflows has resulted in a new paradigm of AI-assisted decision making,in which an AI model provides decision recommendations while humans make the final decisions. To best support humans in decision making, it is critical to obtain a quantitative understanding of how humans interact with and rely on AI. Previous studies often model humans' reliance on AI as an analytical process, i.e., reliance decisions are made based on cost-benefit analysis. However, theoretical models in psychology suggest that the reliance decisions can often be driven by emotions like humans' trust in AI models. In this paper, we propose a hidden Markov model to capture the affective process underlying the human-AI interaction in AI-assisted decision making, by characterizing how decision makers adjust their trust in AI over time and make reliance decisions based on their trust. Evaluations on real human behavior data collected from human-subject experiments show that the proposed model outperforms various baselines in accurately predicting humans' reliance behavior in AI-assisted decision making. Based on the proposed model, we further provide insights into how humans' trust and reliance dynamics in AI-assisted decision making is influenced by contextual factors like decision stakes and their interaction experiences. 

   more » « less
4. Resource‐rational Models of Human Goal Pursuit

   https://doi.org/10.1111/tops.12562  

   Prystawski, Ben; Mohnert, Florian; Tošić, Mateo; Lieder, Falk (August 2021, Topics in Cognitive Science)

   Abstract Goal‐directed behavior is a deeply important part of human psychology. People constantly set goals for themselves and pursue them in many domains of life. In this paper, we develop computational models that characterize how humans pursue goals in a complex dynamic environment and test how well they describe human behavior in an experiment. Our models are motivated by the principle of resource rationality and draw upon psychological insights about people's limited attention and planning capacities. We find that human goal pursuit is qualitatively different and substantially less efficient than optimal goal pursuit in our simulated environment. Models of goal pursuit based on the principle of resource rationality capture human behavior better than both a model of optimal goal pursuit and heuristics that are not resource‐rational. We conclude that the way humans pursue goals is shaped by the need to achieve goals effectively as well as cognitive costs and constraints on planning and attention. Our findings are an important step toward understanding humans' goal pursuit as cognitive limitations play a crucial role in shaping people's goal‐directed behavior. 

   more » « less
5. Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary

   Li, Zhuoyan; Yin, Ming (December 2024, The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS))

   Recent advances in AI models have increased the integration of AI-based decision aids into the human decision making process. To fully unlock the potential of AI- assisted decision making, researchers have computationally modeled how humans incorporate AI recommendations into their final decisions, and utilized these models to improve human-AI team performance. Meanwhile, due to the “black-box” nature of AI models, providing AI explanations to human decision makers to help them rely on AI recommendations more appropriately has become a common practice. In this paper, we explore whether we can quantitatively model how humans integrate both AI recommendations and explanations into their decision process, and whether this quantitative understanding of human behavior from the learned model can be utilized to manipulate AI explanations, thereby nudging individuals towards making targeted decisions. Our extensive human experiments across various tasks demonstrate that human behavior can be easily influenced by these manipulated explanations towards targeted outcomes, regardless of the intent being adversarial or benign. Furthermore, individuals often fail to detect any anomalies in these explanations, despite their decisions being affected by them. 

   more » « less