3 papers
One Reference or Many? Rethinking Multi-Reference Training for Intermediate-Entropy Text Generation
Maitreya Prafulla Chitale, Ketaki Mangesh Shetye, Yash More +4
Natural language generation (NLG) ranges from highly constrained tasks, such as machine translation, to open-ended tasks like dialogue generation. Between them lie peer-review gene…
Breaking It Down: Domain-Aware Semantic Segmentation for Retrieval Augmented Generation
Aparajitha Allamraju, Maitreya Prafulla Chitale, Hiranmai Sri Adibhatla +2
Document chunking is a crucial component of Retrieval-Augmented Generation (RAG), as it directly affects the retrieval of relevant and precise context. Conventional fixed-length an…
Graph-Guided Passage Retrieval for Author-Centric Structured Feedback
Maitreya Prafulla Chitale, Ketaki Mangesh Shetye, Harshit Gupta +3
Obtaining high-quality, pre-submission feedback is a critical bottleneck in the academic publication lifecycle for researchers. We introduce AutoRev, an automated author-centric fe…