arXiv AI June 9, 2026 By Sina Bagheri Nezhad

Signals Are Not States: Neuro-Symbolic Safeguards for Culturally Aware Classroom AI

arXiv:2603. 22793v2 Announce Type: replace Abstract: Classroom AI systems increasingly infer high-level educational states such as engagement, confusion, collaboration, participation, and instructional quality from multimodal and linguistic signals.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 10

AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models

arXiv:2603.08275v2 Announce Type: replace-cross Abstract: With the global proliferation of Large Language Models (LLMs), cultural safety, defined as the ability to generate respectful and appropriate...

By Hankun Kang, Di Lin, Zhirong Liao, Pengfei Bai, Xinyi Zeng, Jiawei Jiang, Yuanyuan Zhu, Dexi Liu, Tieyun Qian

llms safety

arXiv AI

Jun 18

ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection

arXiv:2606. 18988v1 Announce Type: new Abstract: Multimodal deception detection is critical for identifying fraudulent intentions, yet existing approaches predominantly rely on end to end black--box paradigms.

By Jinhao Song, Shan Liang, Yiqun Yue, Zhuhuayang Zhang, Tianqi Gao

llms reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 6

Framing, Judging, Steering: An Assessable Competency Model for Teach-ing Students to Reason With Generative AI

arXiv:2606. 05983v1 Announce Type: new Abstract: Generative AI makes answers easy and understanding hard, and uncritical use invites cognitive offloading.

By Alexander Apartsin, Yehudit Aperstein

llms

arXiv AI

Aug 17

The Metacognitive Bottleneck: Japanese Riddles Reveal Fundamental Limits of Machine Insight and Self-Evaluation in Reasoning AI

arXiv:2509. 14704v3 Announce Type: replace Abstract: Benchmark saturation and training-data contamination increasingly obscure whether reported gains in large language models (LLMs) reflect genuine advances in reasoning or familiarity with recurring patterns in benchmark problems.

By Masaharu Mizumoto, Dat Nguyen, Zhiheng Han, Xingfu Li, Yo Nakawake, Le Minh Nguyen

llms benchmarks

arXiv AI

Jun 2

Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring Agents

arXiv:2606. 01584v1 Announce Type: cross Abstract: Conversational tutoring agents have been shown to improve learning engagement and student outcomes, and large language models (LLMs) are increasingly used in these systems to provide scalable, personalized feedback.

By Aitor Arronte Alvarez, Naiyi Xie Fincham

llms agents benchmarks safety

arXiv AI

Jun 16

Metacognitive Myopia in Large Language Models

arXiv:2408. 05568v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit potentially harmful biases that reinforce culturally embedded stereotypes, influence moral judgments, or amplify positive evaluations of majority groups.

By Florian Scholten, Tobias R. Rebholz, Mandy H\"utter

llms rag agents

One email a morning, machine-written

Related stories

AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models

ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection

Framing, Judging, Steering: An Assessable Competency Model for Teach-ing Students to Reason With Generative AI

The Metacognitive Bottleneck: Japanese Riddles Reveal Fundamental Limits of Machine Insight and Self-Evaluation in Reasoning AI

Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring Agents

Metacognitive Myopia in Large Language Models