The study found that constraining LLM access, rather than banning it, can preserve students' sense of authorship and encourage more strategic writing behaviors while still providing scaffolding benefi…

This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

This study investigated the stability and prompt-responsiveness of AI tools in classifying the cognitive demand of math tasks, finding that few-shot prompting was a more reliable performance booster t…

This study evaluates LLMs in conversational tutoring to identify high-confidence social biases, finding that state-of-the-art models are often overconfident in their incorrect assessments of stereotyp…

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

The paper demonstrates that LLM performance in zero-shot annotation is significantly limited by the alignment between the model's internal understanding and the task definition, showing that prompt-ba…

The paper proposes an interpretable, AI-driven decision layer that ranks course topics needing attention using multiple student and teacher signals, successfully identifying learning gaps before forma…

The paper introduces an LLM-based pipeline that tags learning resources with structured competencies, achieving strong performance while providing traceable evidence and leveraging graph constraints.

The paper proposes a comprehensive benchmark to systematically audit how varying persona prompts and model choices affect the technical quality and social representativeness of scholar recommendations…

The paper designs and evaluates a triadic LLM-Teacher collaboration system for K-12 writing, finding that strategic labor division between the LLM and teacher effectively improves writing quality but…

The paper introduces Reasoning Exposure Prompting (REP), a method that demonstrates that even when LLMs hide their internal reasoning steps from users, useful reasoning supervision can still be elicit…

The paper introduces Reasoning Exposure Prompting (REP), a method that demonstrates that even when LLMs hide internal reasoning traces from users, useful reasoning supervision can still be elicited th…

This study surveyed higher education practitioners to map their beliefs and behaviors regarding AI integration, finding that while they view AI favorably, institutional barriers and gaps in design-ori…

This paper introduces the Data-Model Compatibility (DMC) metric to quantify how suitable a dataset is for reasoning distillation, showing that optimizing data selection using DMC significantly improve…

This paper investigates the vulnerability of LLM-based automatic grading systems to prompt injection (PI) attacks, demonstrating that current systems are highly susceptible to manipulation that can le…

The paper introduces TRACE, a novel metric that evaluates the logical structure of LLM reasoning (CoT) by integrating Toulmin's argumentation theory, demonstrating that sound reasoning structure corre…

This survey provides a comprehensive analysis of Reasoning Language Model (RLM) adoption across 28 scientific disciplines, revealing significant disparities in RLM maturity across different scientific…

The paper proposes Skill-Conditioned Gated Self-Distillation (SGSD), a novel framework that uses retrieved, potentially noisy skills to guide LLM reasoning, achieving state-of-the-art performance on m…

DenseSteer is a training-free inference-time framework that improves the math reasoning capabilities of small language models by steering their internal representations toward a 'Dense Reasoning' patt…

The study compared LLM-based conversational agents (CAs) and traditional dashboards for industrial decision support, finding that while CAs reduce mental workload in simple tasks, neither interface pr…