Lesley Istead | Searcharxiv

arXiv2026

Make or Take: How Students Navigate Self-Created and Instructor-Provided Cheat Sheets

The use of cheat sheets in exams is often framed as a way to reduce cognitive load and support student performance. However, little is known about how students choose between self-created and instructor-provided cheat sheets, or how these choices relate to their broader approaches to exam preparation. We conducted a longitudinal study in a senior-level undergraduate software requirements course, where students could use either an instructor-provided or a self-created cheat sheet for both the midterm and final exams. Across three survey waves, we received 53, 50, and 44 responses, respectively. 41 students completed all three surveys and formed the longitudinal cohort used to examine how choices and experiences evolved over time, while exam-specific analyses used all available responses from the corresponding wave. Our findings identify several considerations that shaped students' choices, including trust in instructor expertise, the desire for personalization, and preparation efficiency. We further show how students' attitudes shifted over time and how their preferences were reflected in patterns of cheat sheet use, perceived content coverage, and challenges encountered during the exams.

cs.HC↗

arXiv2026

UniMaia: Steering Chess Policies with Language for Human-like Play

Recent advances in large language models have enabled natural language to serve as a flexible interface for controlling complex systems, but often at the cost of large-scale multimodal training or weakened domain-specific inductive biases. In structured decision-making domains such as chess, specialized policy networks achieve strong performance but lack semantic controllability, while prompt-conditioned language models are more flexible yet typically exhibit weaker domain grounding. We propose $\textbf{UniMaia}$, a framework for prompt-conditioned policy modulation that adapts a frozen Lc0-based chess policy network using a parameter-efficient text encoder and a ControlNet-style conditioning mechanism. UniMaia enables semantic control over gameplay, including opening selection and player strength, while preserving the pretrained policy representations. We further introduce $\textbf{UniMaia-Aux}$, which incorporates auxiliary temporal conditioning and behavioral prediction objectives. To support this work, we construct a large-scale metadata-augmented Lichess dataset, develop a semi-automated prompt-generation pipeline, and introduce benchmarks spanning both prompt-conditioned and metadata-conditioned settings. UniMaia achieves state-of-the-art expected accuracy on several prompt-conditioned benchmarks and competitive top-move accuracy on general instruction-following tasks, while remaining competitive with dedicated metadata-conditioned approaches on human move prediction benchmarks. UniMaia-Aux further improves expected accuracy and behavioral modeling across several evaluation settings, with modest trade-offs in top-move accuracy. Overall, our results demonstrate that prompt-conditioned control of domain-specific policy networks is feasible without end-to-end multimodal training, while highlighting trade-offs between controllability and predictive performance.

cs.CL↗