Yifan Song

Yifan Song

Auto-generated profile, based on publicly available information

Yifan Song

University of Illinois Urbana-Champaign, Urbana, IL, USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 June 2023
Verified
Conference Paper
Open access
JSJaromir Savelka
Jaromir Savelka
AAArav Agarwal
Arav Agarwal
CBChristopher Bogart
Christopher Bogart
YSYifan Song
Yifan Song
MSMajd Sakr
Majd Sakr
We evaluated the capability of generative pre-trained transformers (GPT), to pass assessments in introductory and intermediate Python programming courses at the postsecondary level. Discussions of potential uses (e.g., exercise generation, code explanation) and misuses (e.g., cheating) of this emerging technology in programming education have intensified, but to date there has not been a rigorous analysis of the models' capabilities in the realistic context of a full-fledged programming course with diverse set of assessment instruments. We evaluated GPT on three Python courses that employ assessments ranging from simple multiple-choice questions (no code involved) to complex programming projects with code bases distributed into multiple files (599 exercises overall). Further, we studied if and how successfully GPT models leverage feedback provided by an auto-grader. We found that the current models are not capable of passing the full spectrum of assessments typically involved in a Python programming course (55%) in introductory and intermediate courses alike. While the models exhibit remarkable capabilities, including correcting solutions based on auto-grader's feedback, some limitations exist (e.g., poor handling of exercises requiring complex chains of reasoning steps). These findings can be leveraged by instructors wishing to adapt their assessments so that GPT becomes a valuable assistant for a learner as opposed to an end-to-end solution.

24 November 2021 in Advanced Engineering Materials
Verified
Journal Article
Closed access
PDF file
NYNan Yang
Nan Yang
YDYong Deng
Yong Deng
SZShengjie Zhao
Shengjie Zhao
YSYifan Song
Yifan Song
JHJinlun Huang
Jinlun Huang
Nan WuNan Wu
Nan Wu


14 March 2024
Verified
Conference Paper
Open access
YSYifan Song
Yifan Song
YWYuanxin Wang
Yuanxin Wang
MAMarshall An
Marshall An
CBChristopher Bogart
Christopher Bogart
MSMajd Sakr
Majd Sakr
Courses with programming assignments have long faced the issue of academic integrity violations (AIV) where cheating could harm the outcome of student learning. Checking code similarity in students' final submissions is a common way to mitigate this issue. But this single analysis is insufficient as 1) students can refactor their code to evade the check, 2) mere code similarity may not be strong enough evidence to support an AIV case, particularly for simpler assignments that may have similar solutions, and 3) code similarity cannot reveal much about the actual circumstances and behaviors of plagiarism. Due to the lack of supporting data or tools, many educators either abandon solving these challenges or rely on manual approaches that are not feasible at scale. In this paper, we propose a workflow to solve the above challenges for large programming classes by providing supporting evidence of cheating with additional learner data: detailed submission timelines with scores and source code. Running this workflow in a large advanced programming course over several years has helped us identify many cheating cases effectively and efficiently.

13 April 2026
Verified
Conference Paper
Open access
TLTiffany Wenting Li
Tiffany Wenting Li
YSYifan Song
Yifan Song
HSHari Sundaram
Hari Sundaram
KKKarrie Karahalios
Karrie Karahalios
Generative chatbots promise to scale personalized learning. Most publicly available generative chatbots are designed to provide confident and eloquent responses by default, even when hallucinating. Prior work has observed that learners using such chatbots often engage shallowly and fail to detect chatbot errors due to overtrust, cognitive overload, and prioritization of short-term gains. To address these challenges, this work examines two chatbot design options in a STEM learning context: introducing verbal uncertainty and reducing response verbosity. Using Bayesian causal inference and thematic analysis in a quasi-experimental setting, we found that a less verbose chatbot improved detection of errors with logical fallacies, but did not increase the use of alternative resources. A chatbot that always expressed uncertainty reduced the adoption of incorrect chatbot responses, but had mixed effects on learning outcomes, suggesting the need to increase signal credibility and maintain learners’ engagement in the learning process despite chatbot disuse.

1 October 2021 in arXiv
Verified
Preprint
Open access
PDF file
KKKevin Köser
Kevin Köser
YSYifan Song
Yifan Song
LPLasse Petersen
Lasse Petersen
EWEmanuel Wenzlaff
Emanuel Wenzlaff
FWFelix Woelk
Felix Woelk
The majority of Earth's surface lies deep in the oceans, where no surface light reaches. Robots diving down to great depths must bring light sources that create moving illumination patterns in the darkness, such that the same 3D point appears with different color in each image. On top, scattering and attenuation of light in the water makes images appear foggy and typically blueish, the degradation depending on each pixel's distance to its observed seafloor patch, on the local composition of the water and the relative poses and cones of the light sources. Consequently, visual mapping, including image matching and surface albedo estimation, severely suffers from the effects that co-moving light sources produce, and larger mosaic maps from photos are often dominated by lighting effects that obscure the actual seafloor structure. In this contribution a practical approach to estimating and compensating these lighting effects on predominantly homogeneous, flat seafloor regions, as can be found in the Abyssal plains of our oceans, is presented. The method is essentially parameter-free and intended as a preprocessing step to facilitate visual mapping, but already produces convincing lighting artefact compensation up to a global white balance factor. It does not require to be trained beforehand on huge sets of annotated images, which are not available for the deep sea. Rather, we motivate our work by physical models of light propagation, perform robust statistics-based estimates of additive and multiplicative nuisances that avoid explicit parameters for light, camera, water or scene, discuss the breakdown point of the algorithms and show results on imagery captured by robots in several kilometer water depth.