作者位次 #2/6ACL 2026Findings· Findings of ACL
Trustworthy and Explainable Causal Representation Learning in Transformers
Yang Liu · Yinghao Zhang · Lin Liu · Jiuyong Li · Debo Cheng · Zaiwen Feng
摘要
A prevalent approach to interpretable representation learning involves creating a mask that weights the significance of each input feature, followed by deriving a masked representation by applying this mask to the input representation. However, the identifiability of these learned masked represen...