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 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 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…

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.

The paper introduces Rationalize, a role-pair framework that facilitates shared semantic reasoning between humans and AI models to achieve deep alignment of intent and action.

This paper introduces a Hybrid Mixture-of-Experts (HybridMoE) framework and a specialized corpus (Varnika) to significantly improve language models' ability to understand and retain figurative, cultur…

The paper introduces Crafter, a multi-agent harness that significantly improves the generation of editable, publication-quality scientific figures from diverse inputs, addressing the limitations of ex…

The paper introduces FigSIM, the first fine-grained dataset for analyzing suicide memes, which is used to benchmark models across tasks like suicide severity and figurative language detection.

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…

The paper introduces TikStance, a multimodal and context-aware dataset for stance detection in political discussions on TikTok.

The paper introduces SciIntBench, an adversarial benchmark that reveals that LLMs' adherence to research integrity norms is highly sensitive to how the misconduct is framed, often failing when the mis…

The paper introduces SciIntBench, an adversarial benchmark that reveals that LLMs' adherence to research integrity norms is highly sensitive to how the misconduct is framed, failing particularly when…

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 SONAR, a prompt sanitization framework that uses natural language inference metrics to identify and remove malicious instructions injected into LLM prompts, achieving near-zero at…

The paper introduces BioConCal, a supervised scoring mechanism that evaluates biomedical NER candidates surfaced by multiple LLMs, significantly improving the quality of the candidate pool for human c…

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…

The paper introduces a robust, four-mechanism LLM pipeline that generates auditable, evidence-grounded structured trait records for hundreds of thousands of diverse species across multiple taxa.