13 papers
HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation
Yilin Jiang, Fei Tan, Xuanyu Yin +2
Simulated students let researchers test tutoring systems and teaching strategies before real learners are available, but only if the simulation reproduces where a particular learne…
Mapping Arctic Polynyas from Sea Ice Concentration Data Using Hierarchical Partitioning and Differentiated Region Growing: Sensitivity to Threshold and Product Choices
Tianyu Zhang, Haiyi Ren, Zhilun Zhang +4
Accurately delineating Arctic coastal polynyas from sea ice concentration data remains challenging because of complex coastal geometry and spatially heterogeneous ice conditions. W…
ADE: Agentic Data Evolution Framework for Human-Centered Objectives
Yang Yu, Yilin Jiang, Zexuan Fei +6
Aligning large language models to human-centered objectives is difficult when targets are non-executable and context-dependent, limiting reliable verification and scalable supervis…
ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models
Yilin Jiang, Xiaorong Zhu, Fei Tan +9
Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators. These roles place demands that ordinary question answering does…
HACHIMI: Scalable and Controllable Student Persona Generation via Orchestrated Agents
Yilin Jiang, Fei Tan, Xuanyu Yin +2
Student Personas (SPs) are emerging as infrastructure for educational LLMs, yet prior work often relies on ad-hoc prompting or hand-crafted profiles with limited control over educa…
HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents
Shuqi Cao, Jingyi He, Fei Tan
Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions without overwhelming the answer st…
Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models
Zhengnan Guo, Fei Tan
While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to autoregressive (AR) models, their faithfulness, specifically reg…
VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models
Chonghan Liu, Yimin Du, Qi An +8
Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances.…
Learning the Macroeconomic Language
Siddhartha Chib, Fei Tan, Zhixun Zhang
We show how state-of-the-art large language models (LLMs) can be trained effectively on limited historical data for macroeconomic forecasting. We estimate a dynamic stochastic gene…
More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning
Yike Zhao, Simin Guo, Ziqing Yang +3
The reasoning capabilities of Large Language Models (LLMs) play a critical role in many downstream tasks, yet depend strongly on the quality of training data. Despite various propo…
ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning
Yiming Du, Yifan Xiang, Bin Liang +3
Fine-tuning multi-turn dialogue systems requires high-quality supervision but often suffers from degraded performance when exposed to low-quality data. Supervision errors in early…
MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy
Shaoxiong Zhan, Yanlin Lai, Ziyu Lu +3
Large language models have achieved substantial progress in mathematical reasoning, yet their advancement is limited by the scarcity of high-quality, high-difficulty training data.…
EduAlign: Aligning Educational LLMs for Helpfulness, Personalization, and Creativity
Siyu Song, Wentao Liu, Ye Lu +8
Educational language models should pursue three complementary objectives: helpfulness through responsible guidance, personalization to learner needs, and creativity that supports e…