GeDi: Generative Discriminator Guided Sequence Generation

• URL: http://arxiv.org/abs/2009.06367v2
• Date: Thu, 22 Oct 2020 14:14:09 GMT
• Title: GeDi: Generative Discriminator Guided Sequence Generation
• Authors: Ben Krause, Akhilesh Deepak Gotmare, Bryan McCann, Nitish Shirish Keskar, Shafiq Joty, Richard Socher, Nazneen Fatema Rajani
• Abstract summary: We propose GeDi as an efficient method for using smaller LMs as generative discriminators to guide generation from large LMs. We find that GeDi gives stronger controllability than the state of the art method while also achieving generation speeds more than 30 times faster.
• Score: 53.15651536569169
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While large-scale language models (LMs) are able to imitate the distribution of natural language well enough to generate realistic text, it is difficult to control which regions of the distribution they generate. This is especially problematic because datasets used for training large LMs usually contain significant toxicity, hate, bias, and negativity. We propose GeDi as an efficient method for using smaller LMs as generative discriminators to guide generation from large LMs to make them safer and more controllable. GeDi guides generation at each step by computing classification probabilities for all possible next tokens via Bayes rule by normalizing over two class-conditional distributions; one conditioned on the desired attribute, or control code, and another conditioned on the undesired attribute, or anti control code. We find that GeDi gives stronger controllability than the state of the art method while also achieving generation speeds more than 30 times faster. Additionally, training GeDi on only four topics allows us to controllably generate new topics zero-shot from just a keyword, unlocking a new capability that previous controllable generation methods do not have. Lastly, we show that GeDi can make GPT-2 (1.5B parameters) significantly less toxic without sacrificing linguistic quality, making it by far the most practical existing method for detoxifying large language models while maintaining a fast generation speed.

Related papers

• Reinforcement Learning with Token-level Feedback for Controllable Text Generation [16.117006822479407]
  We propose a novel reinforcement learning algorithm named TOLE which formulates TOken-LEvel rewards for controllable text generation. Experimental results show that our algorithm can achieve superior performance on both single-attribute and multi-attribute control tasks.
  arXiv  Detail & Related papers  (2024-03-18T08:18:37Z)
• Prompt Optimization via Adversarial In-Context Learning [51.18075178593142]
  adv-ICL is implemented as a two-player game between a generator and a discriminator. The generator tries to generate realistic enough output to fool the discriminator. We show that adv-ICL results in significant improvements over state-of-the-art prompt optimization techniques.
  arXiv  Detail & Related papers  (2023-12-05T09:44:45Z)
• KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation [24.47531522553703]
  We propose KEST, a novel and efficient self-training framework to handle these problems. KEST utilizes a kernel-based loss, rather than standard cross entropy, to learn from the soft pseudo text produced by a shared non-autoregressive generator. Experiments on three controllable generation tasks demonstrate that KEST significantly improves control accuracy while maintaining comparable text fluency and generation diversity against several strong baselines.
  arXiv  Detail & Related papers  (2023-06-17T19:40:57Z)
• Extrapolating Multilingual Understanding Models as Multilingual Generators [82.1355802012414]
  This paper explores methods to empower multilingual understanding models the generation abilities to get a unified model. We propose a textbfSemantic-textbfGuided textbfAlignment-then-Denoising (SGA) approach to adapt an encoder to a multilingual generator with a small number of new parameters.
  arXiv  Detail & Related papers  (2023-05-22T15:33:21Z)
• Controlled Text Generation with Natural Language Instructions [74.88938055638636]
  InstructCTG is a controlled text generation framework that incorporates different constraints. We first extract the underlying constraints of natural texts through a combination of off-the-shelf NLP tools and simple verbalizes. By prepending natural language descriptions of the constraints and a few demonstrations, we fine-tune a pre-trained language model to incorporate various types of constraints.
  arXiv  Detail & Related papers  (2023-04-27T15:56:34Z)
• Bridging the Gap Between Training and Inference of Bayesian Controllable Language Models [58.990214815032495]
  Large-scale pre-trained language models have achieved great success on natural language generation tasks. BCLMs have been shown to be efficient in controllable language generation. We propose a "Gemini Discriminator" for controllable language generation which alleviates the mismatch problem with a small computational cost.
  arXiv  Detail & Related papers  (2022-06-11T12:52:32Z)
• Generating texts under constraint through discriminator-guided MCTS [1.3750624267664153]
  We formalize constrained generation as a tree exploration process guided by a discriminator. Using a discriminator to guide this generation, rather than fine-tuning the LM, allows to apply the constraint more finely and dynamically. We show that our methods achieves state-of-the-art results in constrained generation, without having to tune the language model.
  arXiv  Detail & Related papers  (2021-09-28T09:29:15Z)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)
• Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation [6.2211479935811775]
  State-of-the-art language models are too large to be trained from scratch in a manageable time. We propose Directed Beam Search (DBS), a plug-and-play method for lexically constrained language generation.
  arXiv  Detail & Related papers  (2020-12-31T03:05:44Z)

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.