5 papers
XITE: Cross-lingual Interpolation for Transfer using Embeddings
Barah Fazili, Preethi Jyothi
Facilitating cross-lingual transfer in multilingual language models remains a critical challenge. Towards this goal, we propose an embedding-based data augmentation technique calle…
Enhancing Multilingual Embeddings via Multi-Way Parallel Text Alignment
Barah Fazili, Koustava Goswami
Multilingual pretraining typically lacks explicit alignment signals, leading to suboptimal cross-lingual alignment in the representation space. In this work, we show that training…
Boosting Zero-Shot Crosslingual Performance using LLM-Based Augmentations with Effective Data Selection
Barah Fazili, Ashish Sunil Agrawal, Preethi Jyothi
Large language models (LLMs) are very proficient text generators. We leverage this capability of LLMs to generate task-specific data via zero-shot prompting and promote cross-lingu…
GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?
Barah Fazili, Koustava Goswami, Natwar Modani +1
Retrieval augmented generation (RAG) with large language models (LLMs) for Question Answering (QA) entails furnishing relevant context within the prompt to facilitate the LLM in an…
Translation Errors Significantly Impact Low-Resource Languages in Cross-Lingual Learning
Ashish Sunil Agrawal, Barah Fazili, Preethi Jyothi
Popular benchmarks (e.g., XNLI) used to evaluate cross-lingual language understanding consist of parallel versions of English evaluation sets in multiple target languages created w…