paper-with-me

Papers

SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control

2022-10-31 · Xiaochuang Han, Sachin Kumar, Yulia Tsvetkov

Despite the growing success of diffusion models in continuous-valued domains (e.g., images), similar efforts for discrete domains such as text have yet to match the performance of autoregressive language models. In this work, we present SSD-LM -- a diffusion-based language model with two key design choices. First, SSD-LM is semi-autoregressive, iteratively generating blocks of text, allowing for flexible output length at decoding time while enabling local bidirectional context updates. Second, it is simplex-based, performing diffusion on the natural vocabulary space rather than a learned latent space, allowing us to incorporate classifier guidance and modular control using off-the-shelf classifiers without any adaptation. We evaluate SSD-LM on unconstrained text generation benchmarks, and show that it matches or outperforms strong autoregressive GPT-2 models across standard quality and diversity metrics, while vastly outperforming diffusion-based baselines. On controlled text generation, SSD-LM also outperforms competitive baselines, with an extra advantage in modularity.

📄 PDF Abstract BibTeX arXiv:2210.17432

Code (2)

xhan77/ssd-lm 공식 구현 pytorch
lyh6560new/p3sum pytorch

Tasks

DiversityLanguage ModelingLanguage ModellingText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

TESS: Text-to-Text Self-Conditioned Simplex Diffusion

2023-05-15 · Rabeeh Karimi Mahabadi, Hamish Ivison, Jaesung Tae, James Henderson 외

Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains. However, applying continuous diffusion models to natural language remains challenging due t…

Natural Language UnderstandingParaphrase GenerationQuestion GenerationQuestion-Generation+2

Diffusion In Diffusion: Reclaiming Global Coherence in Semi-Autoregressive Diffusion

2026-01-20 · Linrui Ma, Yufei Cui, Kai Han, Yunhe Wang arxiv

One of the most compelling features of global discrete diffusion language models is their global bidirectional contextual capability. However, existing block-based diffusion studies tend to introduce autoregressive prior…

Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning

2025-09-18 · Yeongbin Seo, Dongha Lee, Jaehyung Kim, Jinyoung Yeo arxiv

Autoregressive (AR) language models generate text one token at a time, which limits their inference speed. Diffusion-based language models offer a promising alternative, as they can decode multiple tokens in parallel. Ho…

Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing

2025-09-20 · Mengqi Wang, Zhan Liu, Zengrui Jin, Guangzhi Sun 외 arxiv

Diffusion-based large language models (DLLMs) have recently attracted growing interest as an alternative to autoregressive decoders. In this work, we present an empirical study on using the diffusion-based large language…

Speech Recognition

Simple and Effective Masked Diffusion Language Models

2024-06-11 · Subham Sekhar Sahoo, Marianne Arriola, Yair Schiff, Aaron Gokaslan 외

While diffusion models excel at generating high-quality images, prior work reports a significant performance gap between diffusion and autoregressive (AR) methods in language modeling. In this work, we show that simple m…

Language ModelingLanguage ModellingMasked Language Modeling