Author

Jaewon Sok

h-index 1 View on Semantic Scholar

We have 3 of 7 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Jan 2026

Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning

It is shown that attention heads with high BOS sink scores are strongly associated with functional redundancy: such heads, especially in deeper layers, contribute little to predictive performance and effectively serve as dumping grounds for superfluous attention weights.

Jaewon Sok, J. Yeom, Seonghyeon Park et al. · arXiv.org · 8 citations

Preprint Aug 2026

Answer First, Reason Later: When Commitment Order Costs Accuracy in Diffusion Language Models

Masked diffusion language models revise many masked output positions in parallel and call a response answer-first when the final answer commits before the reasoning printed ahead of it, which limits how far the intervention result can be generalized.

J. Yeom, Jaewon Sok, Seonghyeon Park et al. · 3 citations

A NSWER F IRST , R EASON L ATER : C OMMITMENT O RDER IN D IFFUSION LLM S

These results reframe existing window-style samplers, previously motivated by efficiency, as the minimal fix for a reasoning pathology they were never designed to address.

J. Yeom, Jaewon Sok, Seonghyeon Park et al. · 0 citations