Related papers: On Conditional and Compositional Language Model Differentiable Prompting

On Conditional and Compositional Language Model Differentiable Prompting

URL: http://arxiv.org/abs/2307.01446v1
Date: Tue, 4 Jul 2023 02:47:42 GMT
Title: On Conditional and Compositional Language Model Differentiable Prompting
Authors: Jonathan Pilault, Can Liu, Mohit Bansal, Markus Dreyer
Abstract summary: Prompts have been shown to be an effective method to adapt a frozen Pretrained Language Model (PLM) to perform well on downstream tasks. We propose a new model, Prompt Production System (PRopS), which learns to transform task instructions or input metadata, into continuous prompts.
Score: 75.76546041094436
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Prompts have been shown to be an effective method to adapt a frozen Pretrained Language Model (PLM) to perform well on downstream tasks. Prompts can be represented by a human-engineered word sequence or by a learned continuous embedding. In this work, we investigate conditional and compositional differentiable prompting. We propose a new model, Prompt Production System (PRopS), which learns to transform task instructions or input metadata, into continuous prompts that elicit task-specific outputs from the PLM. Our model uses a modular network structure based on our neural formulation of Production Systems, which allows the model to learn discrete rules -- neural functions that learn to specialize in transforming particular prompt input patterns, making it suitable for compositional transfer learning and few-shot learning. We present extensive empirical and theoretical analysis and show that PRopS consistently surpasses other PLM adaptation techniques, and often improves upon fully fine-tuned models, on compositional generalization tasks, controllable summarization and multilingual translation, while needing fewer trainable parameters.

Related papers

Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer [10.338170161831496]
Decision Transformer (DT) has emerged as a promising class of algorithms in offline reinforcement learning (RL) tasks. We introduce the Language model-d Prompt Transformer (LPDT), which leverages pre-trained language models for meta-RL tasks and fine-tunes the model using Low-rank Adaptation (LoRA) Our approach integrates pre-trained language model and RL tasks seamlessly.
arXiv Detail & Related papers (2024-08-02T17:25:34Z)
Limits of Transformer Language Models on Learning to Compose Algorithms [77.2443883991608]
We evaluate training LLaMA models and prompting GPT-4 and Gemini on four tasks demanding to learn a composition of several discrete sub-tasks. Our results indicate that compositional learning in state-of-the-art Transformer language models is highly sample inefficient.
arXiv Detail & Related papers (2024-02-08T16:23:29Z)
Instruction Position Matters in Sequence Generation with Large Language Models [67.87516654892343]
Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization. We propose enhancing the instruction-following capability of LLMs by shifting the position of task instructions after the input sentences.
arXiv Detail & Related papers (2023-08-23T12:36:57Z)
Autoregressive Structured Prediction with Language Models [73.11519625765301]
We describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs. Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at.
arXiv Detail & Related papers (2022-10-26T13:27:26Z)
Towards Unified Prompt Tuning for Few-shot Text Classification [47.71344780587704]
We present the Unified Prompt Tuning (UPT) framework, leading to better few-shot text classification for BERT-style models. In UPT, a novel paradigm Prompt-Options-Verbalizer is proposed for joint prompt learning across different NLP tasks. We also design a self-supervised task named Knowledge-enhanced Selective Masked Language Modeling to improve the PLM's generalization abilities.
arXiv Detail & Related papers (2022-05-11T07:40:45Z)
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)
An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks [112.1942546460814]
We report the first exploration of the prompt tuning paradigm for speech processing tasks based on Generative Spoken Language Model (GSLM) Experiment results show that the prompt tuning technique achieves competitive performance in speech classification tasks with fewer trainable parameters than fine-tuning specialized downstream models.
arXiv Detail & Related papers (2022-03-31T03:26:55Z)
Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little [74.49773960145681]
A possible explanation for the impressive performance of masked language model (MLM)-training is that such models have learned to represent the syntactic structures prevalent in NLP pipelines. In this paper, we propose a different explanation: pre-trains succeed on downstream tasks almost entirely due to their ability to model higher-order word co-occurrence statistics. Our results show that purely distributional information largely explains the success of pre-training, and underscore the importance of curating challenging evaluation datasets that require deeper linguistic knowledge.
arXiv Detail & Related papers (2021-04-14T06:30:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.