Brian Yim

With contemporary social movements related to civil rights, personal freedoms, and tensions in higher education institutions around academic freedom, ideological open-mindedness has become an increasingly popular research topic in recent decades. Such openness has been defined as a disposition to engage meaningfully with novel ideas that may conflict with one’s own, and to accommodate or disregard such views with delicacy, precision, and care (Cormier et al., 2026; Kwong, 2023). Findings on effective interventions to reduce ideological polarization remain limited, highlighting the need for a cohesive review. This review catalogued and analyzed findings on individual differences related to ideological open-mindedness through an exploratory research question: Are there measured individual differences (psychological and demographic variables such as personality traits, political beliefs, and gender) that relate meaningfully to ideological open-mindedness? The search process retained 152 records. Results showed associations between ideological open-mindedness and personality traits, age, gender, sexual orientation, culture, language, political standing, socioeconomic status, religious beliefs, education level and type, personal past experience, competence, personal beliefs and interests, and emotional tendencies. Considering varied associations between individual characteristics and differences in ideological open-mindedness, this review serves as a guide towards better understanding this complex construct as precursor to informing effective interventions.

Psychotherapy process measures like the Experiencing Scale (EXP) offer valuable insight into clinical interactions but are time-intensive to code. Large language models (LLMs) like ChatGPT have the potential to streamline this process, but empirical validation is nascent. This exploratory study aimed to provide a proof-of-concept coding the EXP using ChatGPT with special attention to ethical considerations, limitations, and future directions. ChatGPT was used to code 79 psychotherapy transcripts drawn from the EXP manual. Multiple models of ChatGPT were tested using varied few-shot learning prompt engineering protocols. Data collection occurred in three phases, during which models rated both modal and peak EXP scores for all transcripts. ChatGPT demonstrated moderate agreement with manual reference ratings. An efficient configuration (o3-mini, 5-shot prompting) yielded moderate reliability for both modal EXP scores (ICC[3,1] = .67, 95% CI [.53, .79]) and peak EXP scores (ICC[3,1] = .71, 95% CI [.58, .81]). LLMs may feasibly augment or replace human EXP coders under certain conditions. However, evidence is preliminary and ethical and technical limitations remain. Future research should validate the present methodology using out-of-manual data, assess potential pretraining exposure, and explore locally hosted LLM applications to mitigate privacy concerns.