Tootfinder

Advancing Conversational AI with Shona Slang: A Dataset and Hybrid Model for Digital Inclusion
Happymore Masoka
https://arxiv.org/abs/2509.14249 https://ar…

Advancing Conversational AI with Shona Slang: A Dataset and Hybrid Model for Digital Inclusion
African languages remain underrepresented in natural language processing (NLP), with most corpora limited to formal registers that fail to capture the vibrancy of everyday communication. This work addresses this gap for Shona, a Bantu language spoken in Zimbabwe and Zambia, by introducing a novel Shona--English slang dataset curated from anonymized social media conversations. The dataset is annotated for intent, sentiment, dialogue acts, code-mixing, and tone, and is publicly available at https…

AI, AGI, and learning efficiency
My 4-month-old kid is not DDoSing Wikipedia right now, nor will they ever do so before learning to speak, read, or write. Their entire "training corpus" will not top even 100 million "tokens" before they can speak & understand language, and do so with real intentionally.
Just to emphasize that point: 100 words-per-minute times 60 minutes-per-hour times 12 hours-per-day times 365 days-per-year times 4 years is a mere 105,120,000 words. That's a ludicrously *high* estimate of words-per-minute and hours-per-day, and 4 years old (the age of my other kid) is well after basic speech capabilities are developed in many children, etc. More likely the available "training data" is at least 1 or 2 orders of magnitude less than this.
The point here is that large language models, trained as they are on multiple *billions* of tokens, are not developing their behavioral capabilities in a way that's remotely similar to humans, even if you believe those capabilities are similar (they are by certain very biased ways of measurement; they very much aren't by others). This idea that humans must be naturally good at acquiring language is an old one (see e.g. #AI #LLM #AGI

Simulated Language Acquisition in a Biologically Realistic Model of the Brain
Daniel Mitropolsky, Christos Papadimitriou
https://arxiv.org/abs/2507.11788 h…

Simulated Language Acquisition in a Biologically Realistic Model of the Brain
Despite tremendous progress in neuroscience, we do not have a compelling narrative for the precise way whereby the spiking of neurons in our brain results in high-level cognitive phenomena such as planning and language. We introduce a simple mathematical formulation of six basic and broadly accepted principles of neuroscience: excitatory neurons, brain areas, random synapses, Hebbian plasticity, local inhibition, and inter-area inhibition. We implement a simulated neuromorphic system based on t…

MultimodalHugs: Enabling Sign Language Processing in Hugging Face
Gerard Sant, Zifan Jiang, Carlos Escolano, Amit Moryossef, Mathias M\"uller, Rico Sennrich, Sarah Ebling
https://arxiv.org/abs/2509.09729

MultimodalHugs: Enabling Sign Language Processing in Hugging Face
In recent years, sign language processing (SLP) has gained importance in the general field of Natural Language Processing. However, compared to research on spoken languages, SLP research is hindered by complex ad-hoc code, inadvertently leading to low reproducibility and unfair comparisons. Existing tools that are built for fast and reproducible experimentation, such as Hugging Face, are not flexible enough to seamlessly integrate sign language experiments. This view is confirmed by a survey we…

SpikingBrain Technical Report: Spiking Brain-inspired Large Models
Yuqi Pan, Yupeng Feng, Jinghao Zhuang, Siyu Ding, Zehao Liu, Bohan Sun, Yuhong Chou, Han Xu, Xuerui Qiu, Anlin Deng, Anjie Hu, Peng Zhou, Man Yao, Jibin Wu, Jian Yang, Guoliang Sun, Bo Xu, Guoqi Li
https://arxiv.org/abs/2509.05276

SpikingBrain Technical Report: Spiking Brain-inspired Large Models
Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing. Building large models on non-NVIDIA platforms also poses challenges for stable and efficient training. To address this, we introduce SpikingBrain, a family of brain-inspired models designed for efficient long-context training and inference. SpikingBrain leverages the MetaX GPU …

Continuous Bangla Sign Language Translation: Mitigating the Expense of Gloss Annotation with the Assistance of Graph
Safaeid Hossain Arib, Rabeya Akter, Sejuti Rahman
https://arxiv.org/abs/2508.10687

Continuous Bangla Sign Language Translation: Mitigating the Expense of Gloss Annotation with the Assistance of Graph
Millions of individuals worldwide are affected by deafness and hearing impairment. Sign language serves as a sophisticated means of communication for the deaf and hard of hearing. However, in societies that prioritize spoken languages, sign language often faces underestimation, leading to communication barriers and social exclusion. The Continuous Bangla Sign Language Translation project aims to address this gap by enhancing translation methods. While recent approaches leverage transformer arch…

MultiVox: Benchmarking Voice Assistants for Multimodal Interactions
Ramaneswaran Selvakumar, Ashish Seth, Nishit Anand, Utkarsh Tyagi, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha
https://arxiv.org/abs/2507.10859

MultiVox: Benchmarking Voice Assistants for Multimodal Interactions
The rapid progress of Large Language Models (LLMs) has empowered omni models to act as voice assistants capable of understanding spoken dialogues. These models can process multimodal inputs beyond text, such as speech and visual data, enabling more context-aware interactions. However, current benchmarks fall short in comprehensively evaluating how well these models generate context-aware responses, particularly when it comes to implicitly understanding fine-grained speech characteristics, such …

AI Conversational Tutors in Foreign Language Learning: A Mixed-Methods Evaluation Study
Nikolaos Avouris
https://arxiv.org/abs/2508.05156 https://arxiv.org…

AI Conversational Tutors in Foreign Language Learning: A Mixed-Methods Evaluation Study
This paper focuses on AI tutors in foreign language learning, a field of application of AI tutors with great development, especially during the last years, when great advances in natural language understanding and processing in real time, have been achieved. These tutors attempt to address needs for improving language skills (speaking, or communicative competence, understanding). In this paper, a mixed-methos empirical study on the use of different kinds of state-of-the-art AI tutors for langua…

Bias after Prompting: Persistent Discrimination in Large Language Models
Nivedha Sivakumar, Natalie Mackraz, Samira Khorshidi, Krishna Patel, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff
https://arxiv.org/abs/2509.08146

Bias after Prompting: Persistent Discrimination in Large Language Models
A dangerous assumption that can be made from prior work on the bias transfer hypothesis (BTH) is that biases do not transfer from pre-trained large language models (LLMs) to adapted models. We invalidate this assumption by studying the BTH in causal models under prompt adaptations, as prompting is an extremely popular and accessible adaptation strategy used in real-world applications. In contrast to prior work, we find that biases can transfer through prompting and that popular prompt-based mit…

Natural language processing for African languages
David Ifeoluwa Adelani
https://arxiv.org/abs/2507.00297 https://arxiv.org/pdf/2507.…

Natural language processing for African languages
Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few low-resource languages are included, their data is often noisy, and lack of labeled datasets makes it hard to evaluate performance outside high-resource languages like English. In this dissertation, we focus on languages spoken in Sub-Saharan Africa where all the …