Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning

• URL: http://arxiv.org/abs/2308.12219v2
• Date: Fri, 25 Aug 2023 16:32:31 GMT
• Title: Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
• Authors: Jiasheng Ye, Zaixiang Zheng, Yu Bao, Lihua Qian, Quanquan Gu
• Abstract summary: We show that scaling diffusion language models can effectively make them strong language learners. We build competent diffusion language models at scale by first acquiring knowledge from massive data. Experiments show that scaling diffusion language models consistently improves performance across downstream language tasks.
• Score: 56.03057119008865
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The recent surge of generative AI has been fueled by the generative power of diffusion probabilistic models and the scalable capabilities of large language models. Despite their potential, it remains elusive whether diffusion language models can solve general language tasks comparable to their autoregressive counterparts. This paper demonstrates that scaling diffusion models w.r.t. data, sizes, and tasks can effectively make them strong language learners. We build competent diffusion language models at scale by first acquiring knowledge from massive data via masked language modeling pretraining thanks to their intrinsic connections. We then reprogram pretrained masked language models into diffusion language models via diffusive adaptation, wherein task-specific finetuning and instruction finetuning are explored to unlock their versatility in solving general language tasks. Experiments show that scaling diffusion language models consistently improves performance across downstream language tasks. We further discover that instruction finetuning can elicit zero-shot and few-shot in-context learning abilities that help tackle many unseen tasks by following natural language instructions, and show promise in advanced and challenging abilities such as reasoning.

Related papers

• LlamaTurk: Adapting Open-Source Generative Large Language Models for Low-Resource Language [2.9914612342004503]
  This study explores an alternative solution by adapting large language models, primarily trained on English, to low-resource languages. We assess various strategies, including continual training, instruction fine-tuning, task-specific fine-tuning, and vocabulary extension. The results show that continual training improves language comprehension, as reflected in perplexity scores, and task-specific tuning generally enhances performance of downstream tasks.
  arXiv  Detail & Related papers  (2024-05-13T13:41:59Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• A Cheaper and Better Diffusion Language Model with Soft-Masked Noise [62.719656543880596]
  Masked-Diffuse LM is a novel diffusion model for language modeling, inspired by linguistic features in languages. Specifically, we design a linguistic-informed forward process which adds corruptions to the text through strategically soft-masking to better noise the textual data. We demonstrate that our Masked-Diffuse LM can achieve better generation quality than the state-of-the-art diffusion models with better efficiency.
  arXiv  Detail & Related papers  (2023-04-10T17:58:42Z)
• Latent Diffusion for Language Generation [26.620353485679892]
  Recent attempts to adapt diffusion to language have presented diffusion as an alternative to existing language models. We demonstrate that encoder-decoder language models can be utilized to efficiently learn high-quality language autoencoders. We validate the effectiveness of our approach for unconditional, class-conditional, and sequence-to-sequence language generation.
  arXiv  Detail & Related papers  (2022-12-19T13:57:06Z)
• Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic [14.618731441943847]
  We develop a novel framework that enables language models to be mathematically proficient while retaining their linguistic prowess. Specifically, we offer information-theoretic interventions to overcome the catastrophic forgetting of linguistic skills that occurs while injecting non-linguistic skills into language models.
  arXiv  Detail & Related papers  (2022-11-03T18:53:30Z)
• Language Model Pre-Training with Sparse Latent Typing [66.75786739499604]
  We propose a new pre-training objective, Sparse Latent Typing, which enables the model to sparsely extract sentence-level keywords with diverse latent types. Experimental results show that our model is able to learn interpretable latent type categories in a self-supervised manner without using any external knowledge.
  arXiv  Detail & Related papers  (2022-10-23T00:37:08Z)
• PaLM: Scaling Language Modeling with Pathways [180.69584031908113]
  We trained a 540-billion parameter, densely activated, Transformer language model, which we call Pathways Language Model PaLM. We trained PaLM on 6144 TPU v4 chips using Pathways, a new ML system which enables highly efficient training across multiple TPU Pods. We demonstrate continued benefits of scaling by achieving state-of-the-art few-shot learning results on hundreds of language understanding and generation benchmarks.
  arXiv  Detail & Related papers  (2022-04-05T16:11:45Z)
• Language Models are not Models of Language [0.0]
  Transfer learning has enabled large deep learning neural networks trained on the language modeling task to vastly improve performance. We argue that the term language model is misleading because deep learning models are not theoretical models of language.
  arXiv  Detail & Related papers  (2021-12-13T22:39:46Z)
• Towards Zero-shot Language Modeling [90.80124496312274]
  We construct a neural model that is inductively biased towards learning human languages. We infer this distribution from a sample of typologically diverse training languages. We harness additional language-specific side information as distant supervision for held-out languages.
  arXiv  Detail & Related papers  (2021-08-06T23:49:18Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.