DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models

• URL: http://arxiv.org/abs/2306.11825v2
• Date: Thu, 6 Jun 2024 21:01:09 GMT
• Title: DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
• Authors: Sidi Lu, Wenbo Zhao, Chenyang Tao, Arpit Gupta, Shanchan Wu, Tagyoung Chung, Nanyun Peng,
• Abstract summary: NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models. Vanilla NADO suffers from vanishing gradient for low-probability control signals. We propose a improved version of the NADO algorithm, namely DiNADO, which improves the performance of the NADO algorithm.
• Score: 55.06442277395388
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models. It is designed to avoid catastrophic forgetting while achieving guaranteed convergence to an entropy-maximized closed-form optimal solution with reasonable modeling capacity. Despite the success, several challenges arise when apply NADO to a wide range of scenarios. Vanilla NADO suffers from gradient vanishing for low-probability control signals and is highly reliant on a regularization to satisfy the stochastic version of Bellman equation. In addition, the vanilla implementation of NADO introduces a few additional transformer layers, suffering from a limited capacity especially compared to other finetune-based model adaptation methods like LoRA. In this paper, we propose a improved version of the NADO algorithm, namely DiNADO (norm-Disentangled NeurAlly-Decomposed Oracles), which improves the performance of the NADO algorithm through disentangling the step-wise global norm over the approximated oracle $R$-value for all potential next-tokens, allowing DiNADO to be combined with finetuning methods like LoRA. We discuss in depth how DiNADO achieves better capacity, stability and flexibility with both empirical and theoretical results. Experiments on formality control in machine translation and the lexically constrained generation task CommonGen demonstrates the significance of the improvements.

Related papers

• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• Achieving Constraints in Neural Networks: A Stochastic Augmented Lagrangian Approach [49.1574468325115]
  Regularizing Deep Neural Networks (DNNs) is essential for improving generalizability and preventing overfitting. We propose a novel approach to DNN regularization by framing the training process as a constrained optimization problem. We employ the Augmented Lagrangian (SAL) method to achieve a more flexible and efficient regularization mechanism.
  arXiv  Detail & Related papers  (2023-10-25T13:55:35Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)
• Controllable Text Generation with Neurally-Decomposed Oracle [91.18959622763055]
  We propose a framework to control auto-regressive generation models with NeurAlly-Decomposed Oracle (NADO) We present a closed-form optimal solution to incorporate the token-level guidance into the base model for controllable generation.
  arXiv  Detail & Related papers  (2022-05-27T20:17:53Z)
• Energy-Based Models for Code Generation under Compilability Constraints [2.9176992922046923]
  In this work, we pose the problem of learning to generate compilable code as constraint satisfaction. We define an Energy-Based Model (EBM) representing a pre-trained generative model with an imposed constraint of generating only compilable sequences. We then use the KL-Adaptive Distributional Policy Gradient algorithm to train a generative model approxing the EBM.
  arXiv  Detail & Related papers  (2021-06-09T11:06:32Z)
• An EM Approach to Non-autoregressive Conditional Sequence Generation [49.11858479436565]
  Autoregressive (AR) models have been the dominating approach to conditional sequence generation. Non-autoregressive (NAR) models have been recently proposed to reduce the latency by generating all output tokens in parallel. This paper proposes a new approach that jointly optimize both AR and NAR models in a unified Expectation-Maximization framework.
  arXiv  Detail & Related papers  (2020-06-29T20:58:57Z)
• Bayesian Sparse learning with preconditioned stochastic gradient MCMC and its applications [5.660384137948734]
  The proposed algorithm converges to the correct distribution with a controllable bias under mild conditions. We show that the proposed algorithm canally converge to the correct distribution with a controllable bias under mild conditions.
  arXiv  Detail & Related papers  (2020-06-29T20:57:20Z)

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.