Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Models for minimalist RAG: B1ade 335M Embedding and 1B Parameter Small Language Models
Shreyas Subramanian, Mecit Gungor, Vikram Elango
Language and embedding models used in RAG systems are conventionally assumed to require large-scale pretraining and explicit grounding supervision. We present B1ade, an efficient R…
cs.CL2025
Plan-and-Write: Structure-Guided Length Control for LLMs without Model Retraining
Adewale Akinfaderin, Shreyas Subramanian, Akarsha Sehwag
Length control in Large Language Models (LLMs) is a crucial but under-addressed challenge, with applications ranging from voice interfaces requiring concise responses to research s…