GPT Understands, Too

• URL: http://arxiv.org/abs/2103.10385v2
• Date: Wed, 25 Oct 2023 06:15:58 GMT
• Title: GPT Understands, Too
• Authors: Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, Jie Tang
• Abstract summary: We propose a novel method P-Tuning that employs trainable continuous prompt embeddings in concatenation with discrete prompts. P-Tuning is generally effective for both frozen and tuned language models, under both the fully-supervised and few-shot settings.
• Score: 42.701765107498346
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prompting a pretrained language model with natural language patterns has been proved effective for natural language understanding (NLU). However, our preliminary study reveals that manual discrete prompts often lead to unstable performance -- e.g., changing a single word in the prompt might result in substantial performance drop. We propose a novel method P-Tuning that employs trainable continuous prompt embeddings in concatenation with discrete prompts. Empirically, P-Tuning not only stabilizes training by minimizing the gap between various discrete prompts, but also improves performance by a sizeable margin on a wide range of NLU tasks including LAMA and SuperGLUE. P-Tuning is generally effective for both frozen and tuned language models, under both the fully-supervised and few-shot settings.

Related papers

• PAFT: Prompt-Agnostic Fine-Tuning [11.834072667345957]
  We propose Prompt-Agnostic Fine-Tuning(PAFT), a simple yet effective approach that adjusts dynamically prompts during fine-tuning. PAFT operates in two stages: First, a diverse set of meaningful, synthetic candidate prompts is constructed. Second, during fine-tuning, prompts are randomly sampled from this set to create dynamic training inputs.
  arXiv  Detail & Related papers  (2025-02-18T13:46:47Z)
• PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer [94.23904400441957]
  We introduce perturbation-based regularizers, which can smooth the loss landscape, into prompt tuning. We design two kinds of perturbation-based regularizers, including random-noise-based and adversarial-based. Our new algorithms improve the state-of-the-art prompt tuning methods by 1.94% and 2.34% on SuperGLUE and FewGLUE benchmarks, respectively.
  arXiv  Detail & Related papers  (2023-05-03T20:30:51Z)
• SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning [28.29889045842277]
  Multitask prompted learning can help generalization through a diverse set of tasks at once. We propose SPT, a semi-parametric prompt tuning method for multitask prompted learning.
  arXiv  Detail & Related papers  (2022-12-21T11:18:09Z)
• RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning [84.75064077323098]
  This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL) RLPrompt is flexibly applicable to different types of LMs, such as masked gibberish (e.g., grammaBERT) and left-to-right models (e.g., GPTs) Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing finetuning or prompting methods.
  arXiv  Detail & Related papers  (2022-05-25T07:50:31Z)
• IDPG: An Instance-Dependent Prompt Generation Method [58.45110542003139]
  Prompt tuning is a new, efficient NLP transfer learning paradigm that adds a task-specific prompt in each input instance during the model training stage. We propose a conditional prompt generation method to generate prompts for each input instance.
  arXiv  Detail & Related papers  (2022-04-09T15:45:27Z)
• Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt Tuning [41.15017636192417]
  We present CP-Tuning, the first end-to-end Contrastive Prompt Tuning framework for fine-tuning Language Models. It is integrated with the task-invariant continuous prompt encoding technique with fully trainable prompt parameters. Experiments over a variety of language understanding tasks used in IR systems and different PLMs show that CP-Tuning outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-01T02:24:24Z)
• Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models [82.75572875007755]
  We argue that one of the factors hindering the development of prompt-tuning on NLG tasks is the unfamiliar inputs. This motivates us to propose input-tuning, which fine-tunes both the continuous prompts and the input representations. Our proposed input-tuning is conceptually simple and empirically powerful.
  arXiv  Detail & Related papers  (2022-03-07T05:04:32Z)
• AdaPrompt: Adaptive Model Training for Prompt-based NLP [77.12071707955889]
  We propose AdaPrompt, adaptively retrieving external data for continual pretraining of PLMs. Experimental results on five NLP benchmarks show that AdaPrompt can improve over standard PLMs in few-shot settings. In zero-shot settings, our method outperforms standard prompt-based methods by up to 26.35% relative error reduction.
  arXiv  Detail & Related papers  (2022-02-10T04:04:57Z)
• P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks [17.93703302601565]
  We present a novel empirical finding that properly optimized prompt tuning can be universally effective across a wide range of model scales and NLU tasks. We believe P-Tuning v2 can serve as an alternative to fine-tuning and a strong baseline for future research.
  arXiv  Detail & Related papers  (2021-10-14T17:58:47Z)

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.