2 papers
cs.CL2026
Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA
Haruto Sato, Yuki Tanaka, Ren Nakamura +2
Grounded question answering systems should answer only when the supplied evidence supports the answer. In multi-hop QA, this requirement is difficult because partial evidence can m…
cs.CL2026
Behaviorally Effective LoRA Writes Are Sparse and Structured
Haruto Sato, Yuki Tanaka, Ren Nakamura +2
Low-rank adaptation fixes the rank of the update, but it does not identify which parts of a trained write actually carry behavior. We study that question directly and show that beh…