Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Conformalized Large Language Models under Configuration Shift
Yuqicheng Zhu, Jialin Yu, Lin Li +7
Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets…
cs.LG2026
Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs
Yoav Kor Sade, Arvindh Arun, Rishi Puri +2
GraphRAG conditions language models on subgraphs retrieved from knowledge graphs, encoded via message-passing GNNs. Because these encoders entangle node contributions through itera…
cs.LG2024
Expanding Expressivity in Transformer Models with MöbiusAttention
Anna-Maria Halacheva, Mojtaba Nayyeri, Steffen Staab
Attention mechanisms and Transformer architectures have revolutionized Natural Language Processing (NLP) by enabling exceptional modeling of long-range dependencies and capturing i…