Controllable Generation from Pre-trained Language Models via Inverse
Prompting
- URL: http://arxiv.org/abs/2103.10685v1
- Date: Fri, 19 Mar 2021 08:36:52 GMT
- Title: Controllable Generation from Pre-trained Language Models via Inverse
Prompting
- Authors: Xu Zou, Da Yin, Qingyang Zhong, Hongxia Yang, Zhilin Yang, Jie Tang
- Abstract summary: We propose an innovative method, inverse prompting, to better control text generation.
Inverse prompting uses generated text to inversely predict the prompt during beam search.
Our results show that our proposed method substantially outperforms the baselines.
- Score: 47.23315683944257
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large-scale pre-trained language models have demonstrated strong capabilities
of generating realistic text. However, it remains challenging to control the
generation results. Previous approaches such as prompting are far from
sufficient, which limits the usage of language models. To tackle this
challenge, we propose an innovative method, inverse prompting, to better
control text generation. The core idea of inverse prompting is to use generated
text to inversely predict the prompt during beam search, which enhances the
relevance between the prompt and the generated text and provides better
controllability. Empirically, we pre-train a large-scale Chinese language model
to perform a systematic study using human evaluation on the tasks of
open-domain poem generation and open-domain long-form question answering. Our
results show that our proposed method substantially outperforms the baselines
and that our generation quality is close to human performance on some of the
tasks.
Narrators can try our poem generation demo at
https://pretrain.aminer.cn/apps/poetry.html, while our QA demo can be found at
https://pretrain.aminer.cn/app/qa. For researchers, the code is provided in
https://github.com/THUDM/InversePrompting.
Related papers
- Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation [16.49758711633611]
Large Language Models (LLMs) have shown exceptional language generation capabilities in response to text-based prompts.
In this work, we explore the use of Prompt Tuning to achieve controlled language generation.
We demonstrate the efficacy of our method towards mitigating harmful, toxic, and biased text generated by language models.
arXiv Detail & Related papers (2024-04-08T01:54:28Z) - Retrieval is Accurate Generation [99.24267226311157]
We introduce a novel method that selects context-aware phrases from a collection of supporting documents.
Our model achieves the best performance and the lowest latency among several retrieval-augmented baselines.
arXiv Detail & Related papers (2024-02-27T14:16:19Z) - Vector-Quantized Prompt Learning for Paraphrase Generation [18.40940464497253]
This paper proposes to generate diverse and high-quality paraphrases by exploiting the pre-trained models with instance-dependent prompts.
Extensive experiments demonstrate that the proposed method achieves new state-of-art results on three benchmark datasets.
arXiv Detail & Related papers (2023-11-25T07:13:06Z) - Momentum Decoding: Open-ended Text Generation As Graph Exploration [49.812280360794894]
Open-ended text generation with autoregressive language models (LMs) is one of the core tasks in natural language processing.
We formulate open-ended text generation from a new perspective, i.e., we view it as an exploration process within a directed graph.
We propose a novel decoding method -- textitmomentum decoding -- which encourages the LM to explore new nodes outside the current graph.
arXiv Detail & Related papers (2022-12-05T11:16:47Z) - Facts2Story: Controlling Text Generation by Key Facts [0.0]
We propose a controlled generation task based on expanding a sequence of facts, expressed in natural language, into a longer narrative.
We show that while auto-regressive, unidirectional Language Models such as GPT2 produce better fluency, they struggle to adhere to the requested facts.
We propose a plan-and-cloze model (using fine-tuned XLNet) which produces competitive fluency while adhering to the requested content.
arXiv Detail & Related papers (2020-12-08T10:14:29Z) - Unsupervised Text Generation by Learning from Search [86.51619839836331]
TGLS is a novel framework to unsupervised Text Generation by Learning.
We demonstrate the effectiveness of TGLS on two real-world natural language generation tasks, paraphrase generation and text formalization.
arXiv Detail & Related papers (2020-07-09T04:34:48Z) - POINTER: Constrained Progressive Text Generation via Insertion-based
Generative Pre-training [93.79766670391618]
We present POINTER, a novel insertion-based approach for hard-constrained text generation.
The proposed method operates by progressively inserting new tokens between existing tokens in a parallel manner.
The resulting coarse-to-fine hierarchy makes the generation process intuitive and interpretable.
arXiv Detail & Related papers (2020-05-01T18:11:54Z) - PALM: Pre-training an Autoencoding&Autoregressive Language Model for
Context-conditioned Generation [92.7366819044397]
Self-supervised pre-training has emerged as a powerful technique for natural language understanding and generation.
This work presents PALM with a novel scheme that jointly pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus.
An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks.
arXiv Detail & Related papers (2020-04-14T06:25:36Z)
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.