3 accepted papers
While sparse autoencoders yield features easier to study than individual neurons, their reliable interpretation remains challenging. We propose Query Lens, which extends Logit Lens to provide more comprehensive and faithful interpretations of sparse features. By jointly considering encoder-side key …
Large language models often retain unintended content, prompting growing interest in knowledge unlearning.Recent approaches emphasize localized unlearning, restricting parameter updates to specific regions in an effort to remove target knowledge while preserving unrelated general knowledge. However,
Idioms have long posed a challenge due to their unique linguistic properties, which set them apart from other common expressions. While recent studies have leveraged large language models (LLMs) to handle idioms across various tasks, e.g., idiom-containing sentence generation and idiomatic machine t