Learners using standard keyboard-based LLM workflows during pen-based study face a Referential Barrier and an Expressive Barrier¶

Claim · All claims
Evidence · 1 study · qualitative r2 · q2
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Thematic analysis of a formative study (N=6) identified two barriers in standard workflows: difficulty referencing specific regions and difficulty expressing visual/symbolic intent in text. → formative-1

Evidence¶

formative-1¶

Jeongmin Rhee, Changhee Lee, Hyunwoo Kim, Kiroong Choe, Bohyoung Kim, Sungahn Ko, and Jinwook Seo. 2026. Penquiry: A Pen-based Interactive In-situ Q&A System Leveraging LLMs. https://arxiv.org/abs/2609.19870 doi:10.48550/arxiv.2609.19870

q2 · i? · qualitative · r2

Formative Wizard-of-Oz study with six university students who used LLMs during pen-based learning; thematic analysis of interviews and observation identified the two barriers. The study found learners "resorted to inconvenient workarounds, such as repeatedly capturing screenshots or copying and pasting portions of the document."

"Through thematic analysis of the interview transcripts and observational data, we identified two barriers that hinder effective question-asking when learners rely on standard workflow where they use a keyboard on a separate device during pen-based learning: Referential Barrier and Expressive Barrier."

Discussion¶

Related Claims¶

• Unmediated pen input introduced new pen-specific barriers: lack of visual feedback on referential intent and high interaction cost of handwriting complex queries — related
• Pen input supported deictic referencing: 85% of V1 queries contained at least one visible pen mark, and ease of referencing improved significantly over the baseline — related
• In Study 2, Content Snapping's immediate visual confirmation resolved learners' referential uncertainty about system recognition — related