2 papers
cs.CL2025
RoToR: Towards More Reliable Responses for Order-Invariant Inputs
Soyoung Yoon, Dongha Ahn, Youngwon Lee +3
Mitigating positional bias of language models (LMs) for listwise inputs is a well-known and important problem (e.g., lost-in-the-middle). While zero-shot order-invariant LMs have b…
cs.CL2022
Blank Collapse: Compressing CTC emission for the faster decoding
Minkyu Jung, Ohhyeok Kwon, Seunghyun Seo +1
Connectionist Temporal Classification (CTC) model is a very efficient method for modeling sequences, especially for speech data. In order to use CTC model as an Automatic Speech Re…