Author

Fahim Dalvi

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models

Multimodal foundation models are increasingly used in speech-first assistants that must interpret spoken queries and produce visually grounded decisions. Yet it remains unclear whether semantically equivalent queries yield consistent judgments across modality (text vs. speech) and language (English vs. Arabic). We intr...

Basel Mousi, Fahim Dalvi, S. Chowdhury et al. · 2 citations

#natural language process... Jul 2026

Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs

Neuron steering reinforces dialect in some varieties when the prompt is already dialectal but cannot induce it from MSA prompts, whereas vector steering succeeds in both settings, and Arabic dialects are therefore steerable mainly through distributed rather than localized representations.

K. Elozeiri, Mervat T. Abassy, Omar Kallas et al. · arXiv.org · 0 citations

#artificial intelligence Review Aug 2026

ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation

An overview of the ImageEval 2026 shared task on culturally grounded Arabic multimodal evaluation is presented, covering spoken visual question answering and image-grounded hallucination detection in English and Modern Standard Arabic, and CRAI-Bench, evaluating the cultural accuracy of text-to-image generation.

Samir Abdaljalil, Hunzalah Hassan Bhatti, Ahlam Bashiti et al. · 0 citations