3 papers
cs.CL2026
Answer First, Reason Later: When Commitment Order Costs Accuracy in Diffusion Language Models
Jewon Yeom, Jaewon Sok, Seonghyeon Park +3
Masked diffusion language models revise many masked output positions in parallel. We call a token committed once it becomes visible and is never masked again, and call a response a…
cs.LG2026
Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects
Hwiyeong Lee, Ingyu Bang, Uiji Hwang +2
While sparse autoencoders provide features more interpretable than individual neurons, reliably characterizing them remains challenging. We propose Query Lens, which extends Logit…
cs.CL2025
Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models
Hwiyeong Lee, Uiji Hwang, Hyelim Lim +1
Large language models often retain unintended content, prompting growing interest in knowledge unlearning. Recent approaches emphasize localized unlearning, restricting parameter u…