Demonstration Augmentation for Zero-shot In-context Learning
- URL: http://arxiv.org/abs/2406.01224v1
- Date: Mon, 3 Jun 2024 11:46:42 GMT
- Title: Demonstration Augmentation for Zero-shot In-context Learning
- Authors: Yi Su, Yunpeng Tai, Yixin Ji, Juntao Li, Bowen Yan, Min Zhang,
- Abstract summary: Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL)
We propose Demonstration Augmentation for In-context Learning (DAIL), which employs the model's previously predicted historical samples as demonstrations for subsequent ones.
Our experiments reveal that DAIL can significantly improve the model's performance over direct zero-shot inference and can even outperform few-shot ICL without any external information.
- Score: 35.210664102352546
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations without the need for parameter updates. However, many studies have highlighted that the model's performance is sensitive to the choice of demonstrations, presenting a significant challenge for practical applications where we lack prior knowledge of user queries. Consequently, we need to construct an extensive demonstration pool and incorporate external databases to assist the model, leading to considerable time and financial costs. In light of this, some recent research has shifted focus towards zero-shot ICL, aiming to reduce the model's reliance on external information by leveraging their inherent generative capabilities. Despite the effectiveness of these approaches, the content generated by the model may be unreliable, and the generation process is time-consuming. To address these issues, we propose Demonstration Augmentation for In-context Learning (DAIL), which employs the model's previously predicted historical samples as demonstrations for subsequent ones. DAIL brings no additional inference cost and does not rely on the model's generative capabilities. Our experiments reveal that DAIL can significantly improve the model's performance over direct zero-shot inference and can even outperform few-shot ICL without any external information.
Related papers
- Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration [90.41908331897639]
Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data.
We present a novel approach, ReverseGen, designed to automatically generate effective training samples.
arXiv Detail & Related papers (2024-10-22T06:43:28Z) - Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning [29.65600202138321]
In high-speed data stream environments, data do not pause to accommodate slow models.
Model's ignorance: the single-pass nature of OCL challenges models to learn effective features within constrained training time.
Model's myopia: the local learning nature of OCL leads the model to adopt overly simplified, task-specific features.
arXiv Detail & Related papers (2024-09-28T05:24:56Z) - Controlling Forgetting with Test-Time Data in Continual Learning [15.455400390299593]
Ongoing Continual Learning research provides techniques to overcome catastrophic forgetting of previous information when new knowledge is acquired.
We argue that test-time data hold great information that can be leveraged in a self supervised manner to refresh the model's memory of previous learned tasks.
arXiv Detail & Related papers (2024-06-19T15:56:21Z) - DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning [75.68193159293425]
In-context learning (ICL) allows transformer-based language models to learn a specific task with a few "task demonstrations" without updating their parameters.
We propose an influence function-based attribution technique, DETAIL, that addresses the specific characteristics of ICL.
We experimentally prove the wide applicability of DETAIL by showing our attribution scores obtained on white-box models are transferable to black-box models in improving model performance.
arXiv Detail & Related papers (2024-05-22T15:52:52Z) - In-context Learning with Retrieved Demonstrations for Language Models: A Survey [23.24271704145876]
Few-shot in-context learners (ICL) are adept at adapting to new tasks with just a few demonstrations in the input context.
Instead of using a fixed set of demonstrations, one recent development is to retrieve demonstrations tailored to each input query.
We discuss and compare different design choices for retrieval models, retrieval training procedures, and inference algorithms.
arXiv Detail & Related papers (2024-01-21T23:34:42Z) - Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines [83.65380507372483]
Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box.
This paper shows how to leverage recent advances in NLP and multi-modal learning to augment a pre-trained model with search engine retrieval.
arXiv Detail & Related papers (2023-11-29T05:33:28Z) - Improving Input-label Mapping with Demonstration Replay for In-context
Learning [67.57288926736923]
In-context learning (ICL) is an emerging capability of large autoregressive language models.
We propose a novel ICL method called Sliding Causal Attention (RdSca)
We show that our method significantly improves the input-label mapping in ICL demonstrations.
arXiv Detail & Related papers (2023-10-30T14:29:41Z) - Dynamic Demonstrations Controller for In-Context Learning [51.3439660534631]
In-Context Learning (ICL) is a new paradigm for natural language processing (NLP), where a large language model observes a small number of demonstrations and a test instance as its input.
Previous studies have revealed that ICL is sensitive to the selection and the ordering of demonstrations.
We propose a Dynamic Demonstrations Controller (D$2$Controller), which can improve the ICL performance by adjusting the number of demonstrations.
arXiv Detail & Related papers (2023-09-30T14:04:22Z) - Large Language Models with Controllable Working Memory [64.71038763708161]
Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP)
What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining.
How the model's world knowledge interacts with the factual information presented in the context remains under explored.
arXiv Detail & Related papers (2022-11-09T18:58:29Z)
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.