SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control
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.
Code (2)
Tasks
DiversityLanguage ModelingLanguage ModellingText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TESS: Text-to-Text Self-Conditioned Simplex Diffusion
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+2Diffusion In Diffusion: Reclaiming Global Coherence in Semi-Autoregressive Diffusion
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
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
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 RecognitionSimple and Effective Masked Diffusion Language Models
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