This paper measures and analyzes the overuse of epanorthosis, a rhetorical figure, in large language models and proposes techniques to mitigate it.

This paper investigates eight rhetorical patterns used by AI systems to induce contemplation and evaluates their impact on user performance, satisfaction, and reflection.

The paper demonstrates that increasing the toxicity of prompts significantly degrades the factual reliability of LLMs, a degradation linked to the selective amplification of perturbation-sensitive nod…

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 introduces FRANZ, a communicative audit framework, to evaluate how LLMs frame responses to subjective questions, finding that LLMs exhibit statistically significant and coupled differences i…

The study found that while contextualizing AI responses reduces their persuasive power, combining this technique with conversational warmth restores persuasiveness, suggesting that user deference to A…

This study compares various authorship attribution methods on Japanese web reviews, finding that while BERT fine-tuning performs best, TF-IDF+LR offers superior stability and efficiency for large-scal…

The paper introduces LFTutor, an intelligent tutoring system leveraging LLMs and Socratic questioning to teach laypeople about logical fallacies, demonstrating its effectiveness in fostering critical…

The paper investigates compositional abilities in LLMs and humans using the Personal Relation Task, finding that LLMs excel at the structured (Intensional) task while humans are better at the real-wor…

The study tests the validity of Portugal's AMALIA language model by examining its ability to follow a construct's theory and not just rely on surface correlates.

This paper reports controlled experiments on prompt-design decisions for instruction-following and context length in AI models, finding significant degradation in performance beyond certain thresholds…

This paper evaluates the performance of large language models on quiz-style questions covering common and niche topics in six European languages, finding significant knowledge gaps and language-depend…

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…

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

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 demonstrates that targeted adaptation of the small language model Phi Silica, using dataset curation and fine-tuning, significantly improves its performance in short-form text rewriting, na…