# Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder

arXiv: https://arxiv.org/abs/2304.04052 · HTML: https://mlsanity.com/paper/2304.04052/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 73 references that are in the map.
- First posted on arXiv 8 Apr 2023.

## Builds on (most cited first, 30 of 47)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth](https://mlsanity.com/paper/2103.03404/) (2021)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)

## Built on by (most cited first, 30 of 44)

- [On decoder-only architecture for speech-to-text and large language model integration](https://mlsanity.com/paper/2307.03917/) (2023)
- [On-Device Language Models: A Comprehensive Review](https://mlsanity.com/paper/2409.00088/) (2024)
- [ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering](https://mlsanity.com/paper/2401.07333/) (2024)
- [Theoretical limitations of multi-layer Transformer](https://mlsanity.com/paper/2412.02975/) (2024)
- [Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance](https://mlsanity.com/paper/2305.13225/) (2023)
- [A Survey of Deep Learning and Foundation Models for Time Series Forecasting](https://mlsanity.com/paper/2401.13912/) (2024)
- [Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models](https://mlsanity.com/paper/2309.08573/) (2023)
- [T5Gemma 2: Seeing, Reading, and Understanding Longer](https://mlsanity.com/paper/2512.14856/) (2025)
- [ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models](https://mlsanity.com/paper/2310.18208/) (2023)
- [Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent](https://mlsanity.com/paper/2407.21646/) (2024)
- [Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis](https://mlsanity.com/paper/2407.05388/) (2024)
- [Decoder-only Streaming Transformer for Simultaneous Translation](https://mlsanity.com/paper/2406.03878/) (2024)
- [Denoising Autoregressive Representation Learning](https://mlsanity.com/paper/2403.05196/) (2024)
- [Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning](https://mlsanity.com/paper/2312.03248/) (2023)
- [Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency](https://mlsanity.com/paper/2505.13499/) (2025)
- [OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch](https://mlsanity.com/paper/2309.10706/) (2023)
- [Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis](https://mlsanity.com/paper/2403.04080/) (2024)
- [Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention](https://mlsanity.com/paper/2411.10156/) (2024)
- [On the Challenges of Fuzzing Techniques via Large Language Models](https://mlsanity.com/paper/2402.00350/) (2024)
- [TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.15752/) (2024)
- [Summarizing long regulatory documents with a multi-step pipeline](https://mlsanity.com/paper/2408.09777/) (2024)
- [Scaling Laws of Decoder-Only Models on the Multilingual Machine Translation Task](https://mlsanity.com/paper/2409.15051/) (2024)
- [Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model](https://mlsanity.com/paper/2510.26622/) (2025)
- [MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation](https://mlsanity.com/paper/2311.12820/) (2023)
- [Strada-LLM: Graph LLM for traffic prediction](https://mlsanity.com/paper/2410.20856/) (2024)
- [HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signals](https://mlsanity.com/paper/2507.13318/) (2025)
- [An Introduction to Natural Language Processing Techniques and Framework for Clinical Implementation in Radiation Oncology](https://mlsanity.com/paper/2311.02205/) (2023)
- [TPPoet: Transformer-Based Persian Poem Generation using Minimal Data and Advanced Decoding Techniques](https://mlsanity.com/paper/2312.02125/) (2023)
- [Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks](https://mlsanity.com/paper/2403.13112/) (2024)
- [Investigating the translation capabilities of Large Language Models trained on parallel data only](https://mlsanity.com/paper/2406.09140/) (2024)

## Abstract (arXiv)

The sequence-to-sequence (seq2seq) task aims at generating the target sequence based on the given input source sequence. Traditionally, most of the seq2seq task is resolved by the Encoder-Decoder framework which requires 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. Despite the significant advancements in applying language models to the seq2seq task, there is still a lack of thorough analysis on the effectiveness of the decoder-only language model architecture. This paper aims to address this gap by conducting a detailed comparison between the encoder-decoder architecture and the decoder-only language model framework through the analysis of a regularized encoder-decoder structure. This structure is designed to replicate all behaviors in the classical decoder-only language model but has an encoder and a decoder making it easier to be compared with the classical encoder-decoder structure. Based on the analysis, we unveil the attention degeneration problem in the language model, namely, as the generation step number grows, less and less attention is focused on the source sequence. To give a quantitative understanding of this problem, we conduct a theoretical sensitivity analysis of the attention output with respect to the source input. Grounded on our analysis, we propose a novel partial attention language model to solve the attention degeneration problem. Experimental results on machine translation, summarization, and data-to-text generation tasks support our analysis and demonstrate the effectiveness of our proposed model.