Papers QNLI
“QNLI” 태그가 달린 논문 19편 · 필터 해제
Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study
Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on…
CoLADenoisingQNLISST-2Privacy-preserving Fine-tuning of Large Language Models through Flatness
The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT. Differential Privacy (DP) techniques are explored in existing work to mitigat…
Knowledge DistillationPrivacy PreservingQNLItext-classification+1Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge
The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. However, this openness also brings significant security…
QNLISST-2NewsQs: Multi-Source Question Generation for the Inquiring Mind
We present NewsQs (news-cues), a dataset that provides question-answer pairs for multiple news documents. To create NewsQs, we augment a traditional multi-document summarization dataset with questions automatically gener…
ArticlesDocument SummarizationMulti-Document SummarizationQNLI+2Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient BERT
Large pre-trained language models have recently gained significant traction due to their improved performance on various down-stream tasks like text classification and question answering, requiring only few epochs of fin…
QNLIQQPQuestion AnsweringSensitivity+3Meta-training with Demonstration Retrieval for Efficient Few-shot Learning
Large language models show impressive results on few-shot NLP tasks. However, these models are memory and computation-intensive. Meta-training allows one to leverage smaller models for few-shot generalization in a domain…
Few-Shot LearningGPUQNLIRetrieval+2How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives
Recently, various intermediate layer distillation (ILD) objectives have been shown to improve compression of BERT models via Knowledge Distillation (KD). However, a comprehensive evaluation of the objectives in both task…
Knowledge DistillationQNLIAbstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning
Combining large language models with logical reasoning enhances their capacity to address problems in a robust and reliable manner. Nevertheless, the intricate nature of logical reasoning poses challenges when gathering …
Abstract Meaning RepresentationContrastive LearningData AugmentationLanguage Modelling+11Two-in-One: A Model Hijacking Attack Against Text Generation Models
Machine learning has progressed significantly in various applications ranging from face recognition to text generation. However, its success has been accompanied by different attacks. Recently a new attack has been propo…
ClassificationFace Recognitionimage-classificationImage Classification+8Few-shot Multimodal Multitask Multilingual Learning
While few-shot learning as a transfer learning paradigm has gained significant traction for scenarios with limited data, it has primarily been explored in the context of building unimodal and unilingual models. Furthermo…
Few-Shot LearningIn-Context LearningNatural Language UnderstandingNER+9An Automatic and Efficient BERT Pruning for Edge AI Systems
With the yearning for deep learning democratization, there are increasing demands to implement Transformer-based natural language processing (NLP) models on resource-constrained devices for low-latency and high accuracy.…
CPUModel CompressionMRPCQNLI+3Learning Rate Curriculum
Most curriculum learning methods require an approach to sort the data samples by difficulty, which is often cumbersome to perform. In this work, we propose a novel curriculum learning approach termed Learning Rate Curric…
Audio ClassificationQNLIRTESpeech Emotion RecognitionEnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English
While cultural backgrounds have been shown to affect linguistic expressions, existing natural language processing (NLP) research on culture modeling is overly coarse-grained and does not examine cultural differences amon…
Cultural Vocal Bursts Intensity PredictionLanguage ModelingLanguage ModellingQNLI+4DAWSON: Data Augmentation using Weak Supervision On Natural Language
We propose a novel data augmentation model for text, using all available data through weak supervision. To improve generalization, recent work in the field uses BERT and masked language modeling to conditionally augment …
Data AugmentationLanguage ModelingLanguage ModellingMasked Language Modeling+4How effective is BERT without word ordering? Implications for language understanding and data privacy
Ordered word sequences contain the rich structures that define language. However, it{'}s often not clear if or how modern pretrained language models utilize these structures. We show that the token representations and se…
EthicsQNLIKI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding
Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. H…
Graph EmbeddingKnowledge Graph EmbeddingKnowledge Graph EmbeddingsKnowledge Graphs+2Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
In this paper, we propose a novel data augmentation method, referred to as Controllable Rewriting based Question Data Augmentation (CRQDA), for machine reading comprehension (MRC), question generation, and question-answe…
Data AugmentationMachine Reading ComprehensionNatural Language InferenceQNLI+5Margin-Based Regularization and Selective Sampling in Deep Neural Networks
We derive a new margin-based regularization formulation, termed multi-margin regularization (MMR), for deep neural networks (DNNs). The MMR is inspired by principles that were applied in margin analysis of shallow linear…
ClassificationGeneral Classificationimage-classificationImage Classification+7On the Importance of Local Information in Transformer Based Models
The self-attention module is a key component of Transformer-based models, wherein each token pays attention to every other token. Recent studies have shown that these heads exhibit syntactic, semantic, or local behaviour…
de-enMRPCQNLIQQP+1