DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation

• URL: http://arxiv.org/abs/2403.01954v3
• Date: Sun, 7 Jul 2024 15:32:31 GMT
• Title: DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation
• Authors: Chen Xu, Tian Lan, Changlong Yu, Wei Wang, Jun Gao, Yu Ji, Qunxi Dong, Kun Qian, Piji Li, Wei Bi, Bin Hu,
• Abstract summary: Constrained decoding approaches aim to control the meaning or style of text generated by a Pre-trained Language Model (PLM) using specific target words during inference. We propose a novel decoding framework, DECIDER, which enables us to program rules on how we complete tasks to control a PLM.
• Score: 57.07295906718989
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Constrained decoding approaches aim to control the meaning or style of text generated by a Pre-trained Language Model (PLM) using specific target words during inference. However, these methods often guide plausible continuations by greedily selecting targets, which, while completing the task, may disrupt the natural patterns of human language generation. In this work, we propose a novel decoding framework, DECIDER, which enables us to program rules on how we complete tasks to control a PLM. Differing from previous work, our framework transforms the encouragement of target words into the encouragement of all words that satisfy the rule. Specifically, DECIDER is a dual system where a PLM is equipped with a First-OrderLogic (FOL) reasoner to express and evaluate the rules, and a decision function to merge the outputs from both systems to steer the generation. Experiments on CommonGen and PersonaChat demonstrate that DECIDER can effectively follow given rules to achieve generation tasks in a more human-like manner.

Related papers

• CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation [58.84212778960507]
  We propose CodeGRAG, a Graphical Retrieval Augmented Code Generation framework to enhance the performance of LLMs. CodeGRAG builds the graphical view of code blocks based on the control flow and data flow of them to fill the gap between programming languages and natural language. Various experiments and ablations are done on four datasets including both the C++ and python languages to validate the hard meta-graph prompt, the soft prompting technique, and the effectiveness of the objectives for pretrained GNN expert.
  arXiv  Detail & Related papers  (2024-05-03T02:48:55Z)
• Natural Language as Policies: Reasoning for Coordinate-Level Embodied Control with LLMs [7.746160514029531]
  We demonstrate experimental results with LLMs that address robotics task planning problems. Our approach acquires text descriptions of the task and scene objects, then formulates task planning through natural language reasoning. Our approach is evaluated on a multi-modal prompt simulation benchmark.
  arXiv  Detail & Related papers  (2024-03-20T17:58:12Z)
• Successor Features for Efficient Multisubject Controlled Text Generation [48.37713738712319]
  We introduce SF-GEN, which is grounded in two primary concepts: successor features (SFs) and language model rectification. SF-GEN seamlessly integrates the two to enable dynamic steering of text generation with no need to alter the LLM's parameters. To the best of our knowledge, our research represents the first application of successor features in text generation.
  arXiv  Detail & Related papers  (2023-11-03T00:17:08Z)
• PADL: Language-Directed Physics-Based Character Control [66.517142635815]
  We present PADL, which allows users to issue natural language commands for specifying high-level tasks and low-level skills that a character should perform. We show that our framework can be applied to effectively direct a simulated humanoid character to perform a diverse array of complex motor skills.
  arXiv  Detail & Related papers  (2023-01-31T18:59:22Z)
• Learning to Solve Voxel Building Embodied Tasks from Pixels and Natural Language Instructions [53.21504989297547]
  We propose a new method that combines a language model and reinforcement learning for the task of building objects in a Minecraft-like environment. Our method first generates a set of consistently achievable sub-goals from the instructions and then completes associated sub-tasks with a pre-trained RL policy.
  arXiv  Detail & Related papers  (2022-11-01T18:30:42Z)
• Controllable Natural Language Generation with Contrastive Prefixes [120.12778570283956]
  GPT2 generation utilizes a set of small attribute-specific vectors, called prefixes, to steer natural language generation. We propose a novel supervised method and also an unsupervised method to train the prefixes for single-aspect control. Experimental results on both single-aspect and multi-aspect control show that our methods can guide generation towards the desired attributes while keeping high linguistic quality.
  arXiv  Detail & Related papers  (2022-02-27T00:31:03Z)
• Natural Language Specification of Reinforcement Learning Policies through Differentiable Decision Trees [10.406631494442683]
  Human-AI policy specification is a novel procedure we define in which humans can collaboratively warm-start a robot's reinforcement learning policy. We develop a novel collaborative framework to allow humans to initialize and interpret an autonomous agent's behavior. Our approach warm-starts an RL agent by utilizing non-expert natural language specifications without incurring the additional domain exploration costs.
  arXiv  Detail & Related papers  (2021-01-18T16:07:00Z)

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.