Robustness of Demonstration-based Learning Under Limited Data Scenario
- URL: http://arxiv.org/abs/2210.10693v1
- Date: Wed, 19 Oct 2022 16:15:04 GMT
- Title: Robustness of Demonstration-based Learning Under Limited Data Scenario
- Authors: Hongxin Zhang, Yanzhe Zhang, Ruiyi Zhang, Diyi Yang
- Abstract summary: Demonstration-based learning has shown great potential in stimulating pretrained language models' ability under limited data scenario.
Why such demonstrations are beneficial for the learning process remains unclear since there is no explicit alignment between the demonstrations and the predictions.
In this paper, we design pathological demonstrations by gradually removing intuitively useful information from the standard ones to take a deep dive of the robustness of demonstration-based sequence labeling.
- Score: 54.912936555876826
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Demonstration-based learning has shown great potential in stimulating
pretrained language models' ability under limited data scenario. Simply
augmenting the input with some demonstrations can significantly improve
performance on few-shot NER. However, why such demonstrations are beneficial
for the learning process remains unclear since there is no explicit alignment
between the demonstrations and the predictions. In this paper, we design
pathological demonstrations by gradually removing intuitively useful
information from the standard ones to take a deep dive of the robustness of
demonstration-based sequence labeling and show that (1) demonstrations composed
of random tokens still make the model a better few-shot learner; (2) the length
of random demonstrations and the relevance of random tokens are the main
factors affecting the performance; (3) demonstrations increase the confidence
of model predictions on captured superficial patterns. We have publicly
released our code at https://github.com/SALT-NLP/RobustDemo.
Related papers
- 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) - Scaling In-Context Demonstrations with Structured Attention [75.41845145597875]
We propose a better architectural design for in-context learning.
Structured Attention for In-Context Learning replaces the full-attention by a structured attention mechanism.
We show that SAICL achieves comparable or better performance than full attention while obtaining up to 3.4x inference speed-up.
arXiv Detail & Related papers (2023-07-05T23:26:01Z) - SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign
Language Understanding [132.78015553111234]
Hand gesture serves as a crucial role during the expression of sign language.
Current deep learning based methods for sign language understanding (SLU) are prone to over-fitting due to insufficient sign data resource.
We propose the first self-supervised pre-trainable SignBERT+ framework with model-aware hand prior incorporated.
arXiv Detail & Related papers (2023-05-08T17:16:38Z) - Extraneousness-Aware Imitation Learning [25.60384350984274]
Extraneousness-Aware Learning (EIL) learns visuomotor policies from third-person demonstrations with extraneous subsequences.
EIL learns action-conditioned observation embeddings in a self-supervised manner and retrieves task-relevant observations across visual demonstrations.
Experimental results show that EIL outperforms strong baselines and achieves comparable policies to those trained with perfect demonstration.
arXiv Detail & Related papers (2022-10-04T04:42:26Z) - Self-Generated In-Context Learning: Leveraging Auto-regressive Language
Models as a Demonstration Generator [22.532627423361177]
Self-generated in-context learning (SG-ICL) generates demonstrations for in-context learning from PLM itself.
We show SG-ICL significantly outperforms zero-shot learning and is generally worth approximately 0.6 gold training samples.
arXiv Detail & Related papers (2022-06-16T10:52:13Z) - Evaluating the Effectiveness of Corrective Demonstrations and a Low-Cost
Sensor for Dexterous Manipulation [0.5669790037378094]
Imitation learning is a promising approach to help robots acquire dexterous manipulation capabilities.
We investigate characteristics of such additional demonstrations and their impact on performance.
We show that inexpensive vision-based sensors, such as LeapMotion, can be used to dramatically reduce the cost of providing demonstrations.
arXiv Detail & Related papers (2022-04-15T19:55:46Z) - Contrastive Demonstration Tuning for Pre-trained Language Models [59.90340768724675]
Demonstration examples are crucial for an excellent final performance of prompt-tuning.
The proposed approach can be: (i) Plugged into any previous prompt-tuning approaches; (ii) Extended to widespread classification tasks with a large number of categories.
Experimental results on 16 datasets illustrate that our method integrated with previous approaches LM-BFF and P-tuning can yield better performance.
arXiv Detail & Related papers (2022-04-09T05:30:48Z) - Rethinking the Role of Demonstrations: What Makes In-Context Learning
Work? [112.72413411257662]
Large language models (LMs) are able to in-context learn by conditioning on a few input-label pairs (demonstrations) and making predictions for new inputs.
We show that ground truth demonstrations are in fact not required -- randomly replacing labels in the demonstrations barely hurts performance.
We find that other aspects of the demonstrations are the key drivers of end task performance.
arXiv Detail & Related papers (2022-02-25T17:25:19Z) - Learning from Imperfect Demonstrations from Agents with Varying Dynamics [29.94164262533282]
We develop a metric composed of a feasibility score and an optimality score to measure how useful a demonstration is for imitation learning.
Our experiments on four environments in simulation and on a real robot show improved learned policies with higher expected return.
arXiv Detail & Related papers (2021-03-10T07:39:38Z) - Robust Maximum Entropy Behavior Cloning [15.713997170792842]
Imitation learning (IL) algorithms use expert demonstrations to learn a specific task.
Most of the existing approaches assume that all expert demonstrations are reliable and trustworthy, but what if there exist some adversarial demonstrations among the given data-set?
We propose a novel general frame-work to directly generate a policy from demonstrations that autonomously detect the adversarial demonstrations and exclude them from the data set.
arXiv Detail & Related papers (2021-01-04T22:08:46Z)
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.