research
∙
06/05/2023
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
An emerging solution for explaining Transformer-based models is to use v...
share
research
∙
05/23/2023
RET-LLM: Towards a General Read-Write Memory for Large Language Models
Large language models (LLMs) have significantly advanced the field of na...
research
∙
02/06/2023
Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities
Several proposals have been put forward in recent years for improving ou...
research
∙
11/10/2022
BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning
Current pre-trained language models rely on large datasets for achieving...
research
∙
05/06/2022
GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
There has been a growing interest in interpreting the underlying dynamic...
research
∙
03/16/2022
AdapLeR: Speeding up Inference by Adaptive Length Reduction
Pre-trained language models have shown stellar performance in various do...
research
∙
09/13/2021
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations
Most of the recent works on probing representations have focused on BERT...
research
∙
04/03/2021