paper-with-me

홈 › Papers

Substance Beats Style: Why Beginning Students Fail to Code with LLMs

2024-10-15 · Francesca Lucchetti, Zixuan Wu, Arjun Guha, Molly Q Feldman, Carolyn Jane Anderson

Although LLMs are increasing the productivity of professional programmers, existing work shows that beginners struggle to prompt LLMs to solve text-to-code tasks. Why is this the case? This paper explores two competing hypotheses about the cause of student-LLM miscommunication: (1) students simply lack the technical vocabulary needed to write good prompts, and (2) students do not understand the extent of information that LLMs need to solve code generation tasks. We study (1) with a causal intervention experiment on technical vocabulary and (2) by analyzing graphs that abstract how students edit prompts and the different failures that they encounter. We find that substance beats style: a poor grasp of technical vocabulary is merely correlated with prompt failure; that the information content of prompts predicts success; that students get stuck making trivial edits; and more. Our findings have implications for the use of LLMs in programming education, and for efforts to make computing more accessible with LLMs.

📄 PDF Abstract BibTeX arXiv:2410.19792

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation

2026-08-03 · Fengxian Ji, Yuke Li, Jingpu Yang, Juanfan Wu 외 arxiv

However, whether these judges truly evaluate the scientific substance of ideas or are influenced by superficial stylistic presentation remains an open question. To address this question, we propose SciStyleBench, a unifi…

Content vs. Form: What Drives the Writing Score Gap Across Socioeconomic Backgrounds? A Generated Panel Approach

2026-01-06 · Nadav Kunievsky, Pedro Pertusi arxiv

Students from different socioeconomic backgrounds exhibit persistent gaps in test scores, gaps that can translate into unequal educational and labor-market outcomes later in life. In many assessments, performance reflect…

Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking

2024-09-23 · Benjamin Feuer, Micah Goldblum, Teresa Datta, Sanjana Nambiar 외

The release of ChatGPT in November 2022 sparked an explosion of interest in post-training and an avalanche of new preference optimization (PO) methods. These methods claim superior alignment by virtue of better correspon…

BenchmarkingDiversityInstruction FollowingWorld Knowledge

Bots and Blocks: Presenting a project-based approach for robotics education

2026-03-15 · Tobias Geger, Dominique Briechle, Andreas Rausch arxiv

To prepare students for upcoming trends and challenges, it is important to teach them about the helpful and important aspects of modern technologies, such as robotics. However, classic study programs often fail to prepar…

Economic Networks: Theory and Computation

2022-03-22 · Thomas J. Sargent, John Stachurski

This textbook is an introduction to economic networks, intended for students and researchers in the fields of economics and applied mathematics. The textbook emphasizes quantitative modeling, with the main underlying too…