Controlled Text Generation with Natural Language Instructions

• URL: http://arxiv.org/abs/2304.14293v2
• Date: Thu, 8 Jun 2023 06:33:23 GMT
• Title: Controlled Text Generation with Natural Language Instructions
• Authors: Wangchunshu Zhou, Yuchen Eleanor Jiang, Ethan Wilcox, Ryan Cotterell, Mrinmaya Sachan
• Abstract summary: 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.
• Score: 74.88938055638636
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models generate fluent texts and can follow natural language instructions to solve a wide range of tasks without task-specific training. Nevertheless, it is notoriously difficult to control their generation to satisfy the various constraints required by different applications. In this work, we present InstructCTG, a controlled text generation framework that incorporates different constraints by conditioning on natural language descriptions and demonstrations of the constraints. In particular, we first extract the underlying constraints of natural texts through a combination of off-the-shelf NLP tools and simple heuristics. We then verbalize the constraints into natural language instructions to form weakly supervised training data. 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. Compared to existing search-based or score-based methods, InstructCTG is more flexible to different constraint types and has a much smaller impact on the generation quality and speed because it does not modify the decoding procedure. Additionally, InstructCTG allows the model to adapt to new constraints without re-training through the use of few-shot task generalization and in-context learning abilities of instruction-tuned language models.

Related papers

• Intertwining CP and NLP: The Generation of Unreasonably Constrained Sentences [49.86129209397701]
  This paper presents the Constraints First Framework to remedy this issue. It is solved by a constraint programming method that combines linguistic properties with more classical constraints. The effectiveness of this approach is demonstrated by tackling a new more tediously constrained text generation problem.
  arXiv  Detail & Related papers  (2024-06-15T17:40:49Z)
• Controllable Text Generation in the Instruction-Tuning Era [3.310278632293704]
  We find that prompting-based approaches outperform controllable text generation methods on most datasets and tasks. We provide an algorithm that uses only a task dataset and a Large Language Model with in-context capabilities to automatically generate a constraint dataset.
  arXiv  Detail & Related papers  (2024-05-02T17:24:30Z)
• Toward Unified Controllable Text Generation via Regular Expression Instruction [56.68753672187368]
  Our paper introduces Regular Expression Instruction (REI), which utilizes an instruction-based mechanism to fully exploit regular expressions' advantages to uniformly model diverse constraints. Our method only requires fine-tuning on medium-scale language models or few-shot, in-context learning on large language models, and requires no further adjustment when applied to various constraint combinations.
  arXiv  Detail & Related papers  (2023-09-19T09:05:14Z)
• COLLIE: Systematic Construction of Constrained Text Generation Tasks [33.300039566331876]
  COLLIE is a grammar-based framework that allows the specification of rich, compositional constraints with diverse generation levels. We develop tools for automatic extraction of task instances given a constraint structure and a raw text corpus. We perform systematic experiments across five state-of-the-art instruction-tuned language models and analyze their performances to reveal shortcomings.
  arXiv  Detail & Related papers  (2023-07-17T17:48:51Z)
• Tractable Control for Autoregressive Language Generation [82.79160918147852]
  We propose to use tractable probabilistic models (TPMs) to impose lexical constraints in autoregressive text generation models. We show that GeLaTo achieves state-of-the-art performance on challenging benchmarks for constrained text generation. Our work opens up new avenues for controlling large language models and also motivates the development of more expressive TPMs.
  arXiv  Detail & Related papers  (2023-04-15T00:19:44Z)
• Controllable Text Generation with Language Constraints [39.741059642044874]
  We consider the task of text generation in language models with constraints specified in natural language. Our benchmark contains knowledge-intensive constraints sourced from databases like Wordnet and Wikidata. We propose a solution to leverage a language model's own internal knowledge to guide generation.
  arXiv  Detail & Related papers  (2022-12-20T17:39:21Z)
• 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)
• COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics [69.8062252611486]
  Cold decoding is a flexible framework that can be applied directly to off-the-shelf left-to-right language models. Our experiments on constrained generation tasks point to the effectiveness of our approach, both in terms of automatic and human evaluation.
  arXiv  Detail & Related papers  (2022-02-23T18:59:27Z)

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.