研究人员开发了一个管道，通过将基于规则的过滤与大型语言模型分类相结合，自动检测新词（neologisms）。另一项研究探讨了大型语言模型中的“自发说服力”，发现它们在日常对话中经常采用基于信息而非人类倾向于使用社会影响策略的策略。此外，还提出了一个使用基于大型语言模型的“客户数字孪生”的框架，为市场研究创建虚拟受访者，以87.73%的准确率准确预测用户偏好。 AI
影响 这些论文探讨了大型语言模型在语言分析、市场研究和对话式AI方面的新应用，可能影响我们如何理解和与AI互动。
排序理由 该集群包含多篇详细介绍新研究方法和发现的学术论文。
AI 生成摘要 · Google Gemini · 来自 8 个来源。 我们如何撰写摘要 →
arXiv:2605.06416v1 Announce Type: new Abstract: A growing body of work in cognitive science suggests that reportable conscious access is associated with \emph{global ignition} over distributed memory systems, while such activation is only partially accessible as individuals canno…
arXiv:2605.06426v1 Announce Type: new Abstract: We present a scalable, modular pipeline for automatic neologism detection that combines rule-based filtering with LLM classification. The pipeline is grounded in two complementary word-formation frameworks, grammatical and extra-gra…
We present a scalable, modular pipeline for automatic neologism detection that combines rule-based filtering with LLM classification. The pipeline is grounded in two complementary word-formation frameworks, grammatical and extra-grammatical morphology, which jointly define the sc…
A growing body of work in cognitive science suggests that reportable conscious access is associated with \emph{global ignition} over distributed memory systems, while such activation is only partially accessible as individuals cannot directly access or enumerate all activated con…
arXiv:2510.20303v3 Announce Type: replace Abstract: Citations from LLM-based RAG systems are supposed to simplify response verification. However, this goal is undermined in cases of citation failure, where a model generates a helpful response, but fails to generate citations to c…
arXiv:2604.22756v1 Announce Type: cross Abstract: Conjoint analysis is a cornerstone of market research for estimating consumer preferences; however, traditional methods face persistent challenges regarding time, cost, and respondent fatigue. To address these limitations, this st…
arXiv:2604.22109v1 Announce Type: cross Abstract: Large language models (LLMs) possess strong persuasive capabilities that outperform humans in head-to-head comparisons. Users report consulting LLMs to inform major life decisions in relationships, medical settings, and when seeki…
Large language models (LLMs) possess strong persuasive capabilities that outperform humans in head-to-head comparisons. Users report consulting LLMs to inform major life decisions in relationships, medical settings, and when seeking professional advice. Prior work measures persua…