Participants favor socially-sourced others' keywords over their own in exploration prompts, deviating from personalized learning expectations¶

Claim · All claims
Evidence · 1 study · associational r1 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Most guide keywords used were contributed by others (68%), not personally provided by the participant. → Pablo Flores Romero 2025

Evidence¶

Pablo Flores Romero 2025¶

Pablo Flores Romero, Kin Nok Nicholas Fung, Guang Rong & Benjamin Ultan Cowley. (2025). Structured human-LLM interaction design reveals exploration and exploitation dynamics in higher education content generation. npj Science of Learning. https://doi.org/10.1038/s41539-025-00332-3

q2 · i? · associational · r1

Keyword-source analysis across 25 structured GPT interactions. "138 out of 204, 68%" of used guide keywords were others' keywords; all participants included others' keywords, and all but five included at least one of their own.

"most of the guide's keywords used by participants corresponded to other's keywords, not personally provided by the participant, instead of their own (138 out of 204, 68%). All participants included others' keywords in their prompts."

Discussion¶

Related Claims¶

• Exploration prompts exclusively use socially-sourced guide keywords while exploitation prompts mainly use GPT-generated keywords — possibly the same claim (merge candidate)
• Exploration prompt frequency is positively correlated with keyword topic diversity in structured human-LLM content generation — related
• Critical thinking negatively correlates with own-keyword use in middle-aged participants (Group 2), with a non-significant similar trend in Group 3 — related
• Exploitation prompts and GPT keywords concentrate in selected rather than discarded scenarios