9.8k citations
- William & MaryUS456 papers
- Thomas Jefferson National Accelerator FacilityUS172 papers
- Argonne National LaboratoryUS88 papers
- University of GlasgowGB86 papers
- University of VirginiaUS86 papers
- Massachusetts Institute of TechnologyUS84 papers
- Centre National de la Recherche ScientifiqueFR78 papers
- Old Dominion UniversityUS75 papers
- A. Alikhanyan National LaboratoryAM74 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR74 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di GenovaIT69 papers
- Florida International UniversityUS68 papers
6 papers · 1 filter
Explore LLM-enabled Tools to Facilitate Imaginal Exposure Exercises for Social Anxiety
Yimeng Wang, Yinzhou Wang, Alicia Hong +1
Social anxiety (SA) is a prevalent mental health challenge that significantly impacts daily social interactions. Imaginal Exposure (IE), a Cognitive Behavioral Therapy (CBT) techni…
Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering
Daniel Rodriguez-Cardenas, Xiaochang Li, Marcos Macedo +5
Large language models for code are advancing fast, yet our ability to evaluate them lags behind. Current benchmarks focus on narrow tasks and single metrics, which hide critical ga…
Designing AI Peers for Collaborative Mathematical Problem Solving with Middle School Students: A Participatory Design Study
Wenhan Lyu, Yimeng Wang, Murong Yue +5
Collaborative problem solving (CPS) is a fundamental practice in middle-school mathematics education; however, student groups frequently stall or struggle without ongoing teacher s…
Detecting and Correcting Hallucinations in LLM-Generated Code via Deterministic AST Analysis
Dipin Khati, Daniel Rodriguez-Cardenas, Paul Pantzer +1
Large Language Models (LLMs) for code generation boost productivity but frequently introduce Knowledge Conflicting Hallucinations (KCHs), subtle, semantic errors, such as non-exist…
Tricky: Towards a Benchmark for Evaluating Human and LLM Error Interactions
Cole Granger, Dipin Khati, Daniel Rodriguez-Cardenas +1
Large language models (LLMs) are increasingly integrated into software development workflows, yet they often introduce subtle logic or data-misuse errors that differ from human bug…
Exploring Customizable Interactive Tools for Therapeutic Homework Support in Mental Health Counseling
Yimeng Wang, Liabette Escamilla, Yinzhou Wang +2
Therapeutic homework (i.e., tasks assigned by therapists for clients to complete between sessions) is essential for effective psychotherapy, yet therapists often interpret fragment…