11 papers
Self-Distillation with Verbal Regularization
Jiazheng Li, Yawei Li, Junru Lu +7
On-policy self-distillation (OPSD) trains a large language model using supervision from a teacher instantiated from the same model as the student. The teacher is conditioned on pri…
CoLearn: An Agentic Tutor that Learns its Learner in a Human--AI Co-Learning Loop
Kailai He, Zhihao Wu, Linhai Zhang +3
Good tutoring adapts to the individual: it tracks what a learner knows, notices why they go wrong, and asks the next question that will help most. Most deployed tutoring tools inst…
Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations
Salvatore Greco, Hainiu Xu, Jacopo Domenicucci +2
LLMs are increasingly deployed as Artificial Moral Advisors (AMA) in a variety of contexts: what kind of conversational patterns should they display? In this paper, we study how AM…
EDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM Grading
Zhihao Wu, Linhai Zhang, Taiyi Wang +4
Reliable rubric grading requires more than accurate score prediction. Each judgement must be grounded in the mark scheme and evidence from the student answer. Existing credit-assig…
SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
Zhenyi Shen, Junru Lu, Lin Gui +4
Sparse attention reduces the quadratic complexity of full self-attention but faces two challenges: (1) an attention gap, where applying sparse attention to full-attention-trained m…
RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following
Junru Lu, Jiazheng Li, Guodong Shen +5
Role-playing is important for Large Language Models (LLMs) to follow diverse instructions while maintaining role identity and the role's pre-defined ability limits. Existing role-p…
Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time
Jiazheng Li, Yuxiang Zhou, Junru Lu +4
Although preference optimization methods have improved reasoning performance in Large Language Models (LLMs), they often lack transparency regarding why one reasoning outcome is pr…
An Automated Explainable Educational Assessment System Built on LLMs
Jiazheng Li, Artem Bobrov, David West +2
In this demo, we present AERA Chat, an automated and explainable educational assessment system designed for interactive and visual evaluations of student responses. This system lev…
AERA Chat: An Interactive Platform for Automated Explainable Student Answer Assessment
Jiazheng Li, Artem Bobrov, Runcong Zhao +2
Explainability in automated student answer scoring systems is critical for building trust and enhancing usability among educators. Yet, generating high-quality assessment rationale…
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
Junru Lu, Jiazheng Li, Siyu An +4
Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a mor…
FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema
Junru Lu, Siyu An, Min Zhang +3
When the quality of naive prompts is carefully optimized by human experts, the task performance of large language models (LLMs) can be significantly improved. However, expert-based…