Related papers: ZeroPrompt: Scaling Prompt-Based Pretraining to 1,…
Retrained large language models (LLMs) have become extensively used across various sub-disciplines of natural language processing (NLP). In NLP, text classification problems have garnered considerable focus, but still faced with some…
Question-answering (QA) tasks often investigate specific question types, knowledge domains, or reasoning skills, leading to specialized models catering to specific categories of QA tasks. While recent research has explored the idea of…
Recent advances in large pretrained language models have increased attention to zero-shot text classification. In particular, models finetuned on natural language inference datasets have been widely adopted as zero-shot classifiers due to…
Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks. However, when applying machine learning methods to new domains, labeled data may not always be available.…
The recent advances in transfer learning techniques and pre-training of large contextualized encoders foster innovation in real-life applications, including dialog assistants. Practical needs of intent recognition require effective data…
Prompting strategies affect LLM reasoning performance, but their role in chart-based QA remains underexplored. We present a systematic evaluation of four widely used prompting paradigms (Zero-Shot, Few-Shot, Zero-Shot Chain-of-Thought, and…
Previous work has shown that there exists a scaling law between the size of Language Models (LMs) and their zero-shot performance on different downstream NLP tasks. In this work, we show that this phenomenon does not hold when evaluating…
This work proposes a challenging yet more realistic setting for zero-shot cross-task generalization: zero-shot instruction following, presuming the existence of a paragraph-style task definition while no demonstrations exist. To better…
State-of-the-art neural language models can now be used to solve ad-hoc language tasks through zero-shot prompting without the need for supervised training. This approach has gained popularity in recent years, and researchers have…
Prompting is a common approach for leveraging LMs in zero-shot settings. However, the underlying mechanisms that enable LMs to perform diverse tasks without task-specific supervision remain poorly understood. Studying the relationship…
Time-series forecasting (TSF) finds broad applications in real-world scenarios. Prompting off-the-shelf Large Language Models (LLMs) demonstrates strong zero-shot TSF capabilities while preserving computational efficiency. However, existing…
Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt tuning provides a simple way to leverage the information in…
Quantization is a promising approach for reducing memory overhead and accelerating inference, especially in large pre-trained language model (PLM) scenarios. While having no access to original training data due to security and privacy…
Data scaling has revolutionized fields like natural language processing and computer vision, providing models with remarkable generalization capabilities. In this paper, we investigate whether similar data scaling laws exist in robotics,…
Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However,…
Pre-trained multilingual language models show significant performance gains for zero-shot cross-lingual model transfer on a wide range of natural language understanding (NLU) tasks. Previously, for zero-shot cross-lingual evaluation,…
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. The Web likely contains the information necessary to excel…
Thanks to the large pre-trained vision-language models (VLMs) like CLIP, we can craft a zero-shot classifier by "prompt", e.g., the confidence score of an image being "[CLASS]" can be obtained by using the VLM provided similarity measure…
Vision-Language Models (VLMs) demonstrate remarkable zero-shot generalization to unseen tasks, but fall short of the performance of supervised methods in generalizing to downstream tasks with limited data. Prompt learning is emerging as a…
Batch prompting is a common technique in large language models (LLMs) used to process multiple inputs simultaneously, aiming to improve computational efficiency. However, as batch sizes increase, performance degradation often occurs due to…