← Search

Aishik Nagar

2 accepted papers

2025

How do Transformer Embeddings Represent Compositions? A Functional Analysis

ACL 2025finding

Compositionality is a key aspect of human intelligence, essential for reasoning and generalization. While transformer-based models have become the de facto standard for many language modeling tasks, little is known about how they represent compound words, and whether these representations are compos…

Cited by 0SourcePDFScholar
2025

uMedSum: A Unified Framework for Clinical Abstractive Summarization

ACL 2025long

Clinical abstractive summarization struggles to balance faithfulness and informativeness, sacrificing key information or introducing confabulations. Techniques like in-context learning and fine-tuning have improved overall summary quality orthogonally, without considering the above issue. Conversely…

Cited by 0SourcePDFScholar