Generating diverse, pedagogically valid stories for Arabic early-grade reading assessments requires balancing tight constraints on vocabulary, reading level, and narrative structure against the need to avoid repetitive plots that undermine assessment validity. We investigate noise steering, injecting calibrated Gaussian perturbations into the internal representations of transformer models at inference time, as a training-free diversity method evaluated across five small Arabic-centric language models (7-9B parameters). We compare four injection strategies against high-temperature sampling baselines, measuring diversity, quality, constraint adherence, and reading grade level. Residual stream noise consistently improves narrative diversity with minimal quality or constraint cost and preserves early-grade reading level across all Arabic-centric models. Attention entropy noise injection (AENI) stabilizes the otherwise unreliable attention-logit noise while recovering quality. High-temperature sampling inflates reading grade level and causes catastrophic collapse on several models. We find internal representation-level perturbation to be a more suitable diversity strategy than output-level stochasticity for constrained educational content generation.
Arabic Automatic Story Generation with Large Language Models
The University of British Columbia（不列颠哥伦比亚大学）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）；Invertible AI（可逆人工智能公司）
Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric Summarization
IBM Research Europe（IBM欧洲研究院）；IBM Research（IBM研究院）；WeChat AI（微信AI）；The Hong Kong University of Science and Technology（香港科技大学）；Nanjing University of Information Science and Technology（南京信息工程大学）；Nankai University（南开大学）
Rensselaer Polytechnic Institute（伦斯勒理工学院）；IBM Research（IBM研究院）；University of Washington（华盛顿大学）；University of Notre Dame（圣母大学）；WeChat AI, Tencent（腾讯微信人工智能）；University of California Irvine（加州大学欧文分校）
Existing question answering (QA) techniques are created mainly to answer questions asked by humans. But in educational applications, teachers often need to decide what questions they should ask, in order to help students to improve their narrative understanding capabilities. We design an automated question-answer generation (QAG) system for this education scenario: given a story book at the kindergarten to eighth-grade level as input, our system can automatically generate QA pairs that are capable of testing a variety of dimensions of a student's comprehension skills. Our proposed QAG model ar…
Qatar Computing Research Institute - Hamad Bin Khalifa University（哈马德·本·哈利法大学卡塔尔计算研究所）；Özyeğin University（奥兹耶金大学）；aiXplain Inc.（aiXplain公司）
NatiQ is end-to-end text-to-speech system for Arabic. Our speech synthesizer uses an encoder-decoder architecture with attention. We used both tacotron-based models (tacotron-1 and tacotron-2) and the faster transformer model for generating mel-spectrograms from characters. We concatenated Tacotron1 with the WaveRNN vocoder, Tacotron2 with the WaveGlow vocoder and ESPnet transformer with the parallel wavegan vocoder to synthesize waveforms from the spectrograms. We used in-house speech data for two voices: 1) neutral male "Hamza"- narrating general content and news, and 2) expressive female "A…
