Showing cs.CEShow all
2 papers · 1 filter
cs.CE2026
Redefining Evaluation Standards: A Unified Framework for Evaluating the Korean Capabilities of Language Models
Hanwool Lee, Dasol Choi, Sooyong Kim +6
Recent advancements in Korean large language models (LLMs) have driven numerous benchmarks and evaluation methods, yet inconsistent protocols cause up to 10 p.p performance gaps ac…
cs.CE2025
(G)I-DLE: Generative Inference via Distribution-preserving Logit Exclusion with KL Divergence Minimization for Constrained Decoding
Hanwool Lee
We propose (G)I-DLE, a new approach to constrained decoding that leverages KL divergence minimization to preserve the intrinsic conditional probability distribution of autoregressi…