TL;DR
This work introduces a minimal "observer-effect" prompting technique, which demonstrates that subtle social-facilitation cues can reliably activate higher vigilance in LLMs without the need for additional reasoning instructions.
A benchmark for evaluating whether LLMs can recover situated pragmatic meanings in Chinese online comments is introduced, and case analysis shows that models often recognize broad irony or playfulness while misidentifying the mechanism or interactional move.
Large language models (LLMs) increasingly mediate human communication, from drafting emails to summarizing scientific reports, yet whether they faithfully preserve a speaker's position remains largely untested. We model AI-mediated communication as a two-step generation-extraction pipeline: one LLM produces an argument...
The findings validate that LLMs can effectively detect strategic narratives in a zero-shot setting and when combined with simple ensembling and human-written descriptions, they can rival supervised systems, offering a scalable solution for narrative detection, specially when there is no training data for the vast major...
An integrated conceptual frame-work that couples attention- and perturbation-based explainability with lightweight hallucination-detection signals and token-efficient inference strategies is presented, and a set of cross-cutting consistency metrics are instrumented with a set of cross-cutting consistency metrics.
Conversational database interfaces face a critical challenge: users naturally embed queries in conversational noise (greetings, politeness, off-topic remarks), which degrades intent classification accuracy and wastes computational resources. Despite advances in orchestration and retrieval strategies, a fundamental ques...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
