This study compares different levels of LLM access in a statistics course, finding that structured, guided use significantly improves students' reasoning skills and independent learning compared to un…

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

This paper shows that large language models can automate reproducibility assessments in the social and behavioral sciences.

This paper evaluates the performance of a Large Language Model (LLM) in a high-stakes context by comparing it to human experts and measuring variance and error magnitude.

This paper evaluates the performance of a Large Language Model (LLM) in a high-stakes context by comparing it to human experts and measuring variance and error magnitude.

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…

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 proposes SteganoPrompt, an input-side watermark embedded in the assignment prompt that forces LLMs to generate a detectable signature in their output, thereby exposing verbatim copy-pasting.

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 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…

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…

The paper introduces PRAIB, a benchmark that demonstrates that LLM-generated peer reviews, while often verbose, systematically diverge from human norms by being less variable, positively biased, and f…

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

This study demonstrates that the tone of a prompt significantly affects the accuracy of various LLMs, requiring users to exercise caution regarding tone-robust reliability.

Permit is a novel framework that enforces fine-grained, permission-aware control over the hidden states of LLMs, preventing information leakage even when sensitive data is present in the context.

The paper demonstrates 'argument collapse,' showing that LLMs tend to converge on a small, repetitive set of polished arguments when generating long-form public debates, significantly reducing the div…

This paper introduces 'implicit identity' as a unifying framework to survey and categorize LLM fingerprinting and watermarking techniques for verifying ownership and provenance across datasets, models…

The paper demonstrates that using English prompts causes large language models to prioritize globally dominant narratives over local cultural knowledge, even when local evidence is provided.

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…