Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Understanding Target Probability Reuse in Speculative Decoding
Jungseob Lee, Giyoon Jang, Chailin Nam +6
Speculative decoding uses a target model to verify a tree of draft tokens in parallel. We study whether the resulting next-token distributions can help select the next tree. For un…
cs.CL2026
OMIT the Action: Measuring Framing-Invariant Omission Bias under Philosophical Disagreement
Sihyeon Lee, Jihun Song, Chanwoo Kim +2
As LLMs increasingly assist in moral reasoning, omission bias, the tendency to prefer inaction even when equivalent framings reverse substantive outcomes, poses a significant risk…