Psychology

Some notes on the Paper “Psychological Aspects in Retrieval and Recommendation” published in SIGIR 2025, together with its slides available at: https://github.com/aisocietylab/Psy-IR-RecSys-SIGIR25/tree/main. The tutorial focuses on three key psychological topics and sheds light on how they influence and manifest in the IR and RS ecosystem: cognitive architectures, cognitive effects and biases, and personality and affect. Motivation Understanding human cognition, decision-making processes, and psychological factors is important to enable user-centric retrieval and recommendation systems. ...

Here are just some notes taken while I was reading. Recently, some research has suggested that LLMs may even be able to simulate human psychology and can therefore replace human participants in psychological studies. We caution against this approach. First, we provide conceptual arguments against the hypothesis that LLMs simulate human psychology. We then present empiric evidence illustrating our arguments by demonstrating that slight changes to wording that correspond to large changes in meaning lead to notable discrepancies between LLMs’ and human responses, even for the recent CENTAUR model that was specifically fine-tuned on psychological responses. Additionally, different LLMs show very different responses to novel items, further illustrating their lack of reliability. We conclude that LLMs do not simulate human psychology and recommend that psychological researchers should treat LLMs as useful but fundamentally unreliable tools that need to be validated against human responses for every new application. ...