LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that seemingly resemble harmful content. This phenomenon diminishes utility in production applications that repeatedly rely on common prompt templates or applications that frequently rely on LLMs for specific tasks (e.g. sentiment analysis, language translation). Through extensive evaluation, we demonstrate that LLMs persist in refusing inputs containing harmful content, even when they are reframed with tasks that have benign intent. Our mechanistic analysis reveals that LLMs follow distinct "constellation" patterns in embedding space as representations traverse layers, with each NLP task maintaining consistent trajectories that shift predictably between refusal and non-refusal cases. We introduce SafeConstellations, an inference-time trajectory-shifting approach that tracks task-specific trajectory patterns and guides representations toward non-refusal pathways. By selectively guiding model behavior only on tasks prone to over-refusal, our method reduces over-refusals with minimal impact on utility—offering a principled and conditional approach to mitigating over-refusals.

Natural Language Understanding (NLU) for low-resource languages remains a major challenge in NLP due to the scarcity of high-quality data and language-specific models. Maithili, despite being spoken by millions, lacks adequate computational resources, limiting its inclusion in digital and AI-driven applications. To address this gap, we introduce maiBERT, a BERT-based language model pre-trained specifically for Maithili using the Masked Language Modeling (MLM) technique. Our model is trained on a newly constructed Maithili corpus and evaluated through a news classification task. In our experiments, maiBERT achieved an accuracy of 87.02%, outperforming existing regional models like NepBERTa and HindiBERT, with a 0.13% overall accuracy gain and 5–7% improvement across various classes. We have open-sourced maiBERT on Hugging Face, enabling further fine-tuning for downstream tasks such as sentiment analysis and Named Entity Recognition (NER).