Papers with layer representations

4 papers
Multilingual, Multi-scale and Multi-layer Visualization of Intermediate Representations (D19-3)

Copied to clipboard

Challenge: Currently, the main alternatives to deal with sequences are Recurrent Neural Networks (RNN) architectures and the Transformer.
Approach: They propose a web-based tool that visualizes the sentence and token representations of RNNs and Transformer architectures at the sentence level.
Outcome: The proposed visualization tool analyses gender inequalities in contextual word embeddings and the common language representation in a multilingual machine translation system.
Quantifying the Contextualization of Word Representations with Semantic Class Probing (2020.findings-emnlp)

Copied to clipboard

Challenge: Pretrained language models are effective in solving NLP tasks, but there are still questions about how and why they work so well.
Approach: They use BERT to quantify contextualization by studying the extent of inference . they show that top layer representations support highly accurate inference of semantic classes .
Outcome: The proposed model is highly accurate, but weak in the lower layers . it is more task-specific after finetuning while lower layers are more transferable .
Choose Your Transformer: Improved Transferability Estimation of Transformer Models on Classification Tasks (2024.findings-acl)

Copied to clipboard

Challenge: Existing models for NLP tasks require fine-tuning, but it is computationally infeasible.
Approach: They propose an approach that inexpensively estimates a ranking of the expected performance of a given set of transformer language models for a specific task.
Outcome: The proposed model improves the Pearson correlation coefficient between the true model ranks and the estimate.
Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning (2025.acl-long)

Copied to clipboard

Challenge: Representation Fine-tuning (ReFT) is a proposed method for improving parameter efficiency . however, it yields suboptimal performance, as fixed-position representations have uncertain impact on outputs .
Approach: They propose a method that fine-tunes critical representations in a low-rank linear subspace while freezing the base model.
Outcome: The proposed method improves accuracy of LLaMA-2-7B and ReFT by 18.2 and 3.8 on GSM8K.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations