Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
Heejin Do · Shashank Sonkar · Mrinmaya Sachan
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Heejin Do · Shashank Sonkar · Mrinmaya Sachan
Sangwon Ryu · Heejin Do · Yunsu Kim · Gary Lee · Jungseul Ok
Controllable summarization moves beyond generic outputs toward human-aligned summaries guided by specified attributes. In practice, the interdependence among attributes makes it challenging for language models to satisfy correlated constraints consistently. Moreover, previous approaches often req...
Jun Seo · Sangwon Ryu · Heejin Do · Hyounghun Kim · Gary Lee
Knowledge Tracing (KT) aims to predict learners’ future performance from past interactions. While recent KT approaches have improved via learning item representations aligned with Knowledge Components, they overlook the procedural dynamics of problem solving. We propose Behavior-Aware Item Modeli...