Related papers: DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers

URL: http://arxiv.org/abs/2310.03686v2
Date: Wed, 3 Apr 2024 12:09:26 GMT
Title: DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
Authors: Anna Langedijk, Hosein Mohebbi, Gabriele Sarti, Willem Zuidema, Jaap Jumelet,
Abstract summary: We propose a simple, new method to analyze encoder-decoder Transformers: DecoderLens. Inspired by the LogitLens (for decoder-only Transformers), this method involves allowing the decoder to cross-attend representations of intermediate encoder layers. We report results from the DecoderLens applied to models trained on question answering, logical reasoning, speech recognition and machine translation.
Score: 6.405360669408265
License: http://creativecommons.org/licenses/by/4.0/
Abstract: In recent years, many interpretability methods have been proposed to help interpret the internal states of Transformer-models, at different levels of precision and complexity. Here, to analyze encoder-decoder Transformers, we propose a simple, new method: DecoderLens. Inspired by the LogitLens (for decoder-only Transformers), this method involves allowing the decoder to cross-attend representations of intermediate encoder layers instead of using the final encoder output, as is normally done in encoder-decoder models. The method thus maps previously uninterpretable vector representations to human-interpretable sequences of words or symbols. We report results from the DecoderLens applied to models trained on question answering, logical reasoning, speech recognition and machine translation. The DecoderLens reveals several specific subtasks that are solved at low or intermediate layers, shedding new light on the information flow inside the encoder component of this important class of models.

Related papers

Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder [75.03283861464365]
The seq2seq task aims at generating the target sequence based on the given input source sequence. Traditionally, most of the seq2seq task is resolved by an encoder to encode the source sequence and a decoder to generate the target text. Recently, a bunch of new approaches have emerged that apply decoder-only language models directly to the seq2seq task.
arXiv Detail & Related papers (2023-04-08T15:44:29Z)
Error Correction Code Transformer [92.10654749898927]
We propose to extend for the first time the Transformer architecture to the soft decoding of linear codes at arbitrary block lengths. We encode each channel's output dimension to high dimension for better representation of the bits information to be processed separately. The proposed approach demonstrates the extreme power and flexibility of Transformers and outperforms existing state-of-the-art neural decoders by large margins at a fraction of their time complexity.
arXiv Detail & Related papers (2022-03-27T15:25:58Z)
Multi-Stream Transformers [10.633944207679274]
Transformer-based encoder-decoder models produce a fused token-wise representation after every encoder layer. We investigate the effects of allowing the encoder to preserve and explore alternative hypotheses, combined at the end of the encoding process.
arXiv Detail & Related papers (2021-07-21T20:16:57Z)
On the Sub-Layer Functionalities of Transformer Decoder [74.83087937309266]
We study how Transformer-based decoders leverage information from the source and target languages. Based on these insights, we demonstrate that the residual feed-forward module in each Transformer decoder layer can be dropped with minimal loss of performance.
arXiv Detail & Related papers (2020-10-06T11:50:54Z)
A Generative Approach to Titling and Clustering Wikipedia Sections [12.154365109117025]
We evaluate transformer encoders with various decoders for information organization through a new task: generation of section headings for Wikipedia articles. Our analysis shows that decoders containing attention mechanisms over the encoder output achieve high-scoring results by generating extractive text. A decoder without attention better facilitates semantic encoding and can be used to generate section embeddings.
arXiv Detail & Related papers (2020-05-22T14:49:07Z)
Rethinking and Improving Natural Language Generation with Layer-Wise Multi-View Decoding [59.48857453699463]
In sequence-to-sequence learning, the decoder relies on the attention mechanism to efficiently extract information from the encoder. Recent work has proposed to use representations from different encoder layers for diversified levels of information. We propose layer-wise multi-view decoding, where for each decoder layer, together with the representations from the last encoder layer, which serve as a global view, those from other encoder layers are supplemented for a stereoscopic view of the source sequences.
arXiv Detail & Related papers (2020-05-16T20:00:39Z)
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models [90.58793284654692]
We take Transformer as the testbed and introduce a layer of gates in-between the encoder and the decoder. The gates are regularized using the expected value of the sparsity-inducing L0penalty. We investigate the effects of this sparsification on two machine translation and two summarization tasks.
arXiv Detail & Related papers (2020-04-24T16:57:52Z)
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers [69.40942736249397]
The way word translation evolves in Transformer layers has not yet been investigated. We show that translation already happens progressively in encoder layers and even in the input embeddings. Our experiments show that we can increase speed by up to a factor 2.3 with small gains in translation quality, while an 18-4 deep encoder configuration boosts translation quality by +1.42 BLEU (En-De) at a speed-up of 1.4.
arXiv Detail & Related papers (2020-03-21T06:12:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.