Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Linger and Lose: Knowledge Collapse in Low-Bit Language Models
Prashanna Mani Paudel, Shivanand Venkanna Sheshappanavar
Training language models with ternary weights is commonly judged by loss and downstream accuracy, which record only a modest cost relative to full precision. We show that these met…
cs.CL2026
Parameter Golf: What Really Works?
Prashanna Mani Paudel, Shivanand Venkanna Sheshappanavar
How far can a language model improve under a strict artifact budget? Parameter Golf posed this question as an open community challenge in which participants trained the best langua…
cs.CL2026
When More Documents Hurt RAG: Measuring and Reducing Vector Search Dilution with Domain-Scoped Retrieval
Nabaraj Subedi, Ahmed Abdelaty, Shivanand Venkanna Sheshappanavar
Retrieval-augmented generation (RAG) degrades when applied to large, heterogeneous document collections. In RAG systems, dense similarity becomes less discriminative, causing top-$…