activity
20242026
most citedFrom Defects to Demands: A Unified, Iterative, and Heuristically Guided LLM-Based Framework for Automated Software Repair and Requirement Realization

1 citations · 1 across the 4 of their papers we have counts for

collaborators

10 papers

cs.HC2026

Teacher-Authored Prompts for Configuring Student-AI Dialogue: K-12 Classroom Implementation

Alex Liu, Min Sun, Lief Esbenshade +3

GenAI has rapidly entered instructional and learning settings as a teaching assistant or AI tutor. However, less is known about how pedagogical intent connects to the learning gene…

cs.HC2025

AI as a Teaching Partner: Early Lessons from Classroom Codesign with Secondary Teachers

Alex Liu, Lief Esbenshade, Shawon Sarkar +6

This report presents a comprehensive account of the Colleague AI Classroom pilot, a collaborative design (co-design) study that brought generative AI technology directly into real…

cs.CR2025

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data

Zi Liang, Qingqing Ye, Xuan Liu +3

Synthetic data refers to artificial samples generated by models. While it has been validated to significantly enhance the performance of large language models (LLMs) during trainin…

cs.HC2025

Emerging Patterns of GenAI Use in K-12 Science and Mathematics Education

Lief Esbenshade, Shawon Sarkar, Drew Nucci +10

In this report, we share findings from a nationally representative survey of US public school math and science teachers, examining current generative AI (GenAI) use, perceptions, c…

cs.HC2025

How K-12 Educators Use AI: LLM-Assisted Qualitative Analysis at Scale

Alex Liu, Lief Esbenshade, Shawon Sarkar +4

This study investigates how K-12 educators use generative AI tools in real-world instructional contexts and how large language models (LLMs) can support scalable qualitative analys…

cs.CL2025

Improving the Distributional Alignment of LLMs using Supervision

Gauri Kambhatla, Sanjana Gautam, Angela Zhang +4

The ability to accurately align LLMs with diverse population groups on subjective questions would have great value. In this work, we show that adding simple supervision can more co…