Morteza Dehghani

Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt. In this paper, we propose Flip-Flop Consistency (F ^2 C), an unsupervised training method that improves robustness to such perturbations. F ^2 C is composed of two key component...

Question answering over visually rich documents (VRDs) requires reasoning not only over isolated content but also over documents’ structural organization and cross-page dependencies. However, conventional retrieval-augmented generation (RAG) methods encode content in isolated chunks during ingest...

Traffic stops are among the most frequent police–civilian interactions, and body-worn cameras (BWCs) provide a unique record of how these encounters unfold. Respect is a central dimension of these interactions, shaping public trust and perceived legitimacy, yet its interpretation is inherently su...