This paper investigates the production-evaluation gap in Large Reasoning Models (LRMs), finding that while LRMs excel at generating solutions, they struggle significantly to evaluate flawed reasoning,…

This paper localizes the attention heads within LLMs responsible for specific reasoning steps, finding that specialized heads handle factual retrieval while higher layers manage global information int…

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 paper investigates the non-monotonic role of sample difficulty in Reinforcement Learning with Verifiable Reward (RLVR), finding that medium-difficulty problems provide the most balanced and benef…

Persona prompting does not universally improve LLM performance; instead, it systematically trades increased expertise depth for reduced clarity, making multi-metric evaluation essential.

This paper explores using Knowledge Components (KCs) as interpretable signals to understand assignment difficulty and student struggle in intro programming courses.

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…

The paper introduces an Item Response Theory (IRT)-based indicator that effectively identifies likely mislabeled items in existing LLM benchmarks, revealing systematic errors in labeling and model spe…

This paper evaluates the reliability of using item response theory (IRT) models for AI benchmarking, comparing four estimation tools under various simulation conditions.

This paper investigates how different types of compressed reasoning data (Explicit, Composed, Implicit CoT) affect LLM performance during post-training, finding that the choice of compression and subs…

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 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 IDEAFix, a systematic evaluation framework designed to analyze how structured prompting and task design influence the divergent thinking and originality of idea generation in LLMs…

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…

The paper introduces Reasoning in Memory (RiM), a latent reasoning method that replaces autoregressive token generation with fixed memory blocks to enable compute-efficient internal working memory for…

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 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 eMoT framework enhances multi-step reasoning in LLMs by treating reasoning as an evolving memory, stabilizing performance through symbolic computation and structured refinement.