Papers SST-2
“SST-2” 태그가 달린 논문 66편 · 필터 해제
LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
Recent efforts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for adapting large language models (LLMs) to multiple tasks still exhibit prevailing limitations: they either swap entire attention/feed-…
ARCCoLAGSM8KHumanEval+4PL-FGSA: A Prompt Learning Framework for Fine-Grained Sentiment Analysis Based on MindSpore
Fine-grained sentiment analysis (FGSA) aims to identify sentiment polarity toward specific aspects within a text, enabling more precise opinion mining in domains such as product reviews and social media. However, traditi…
Aspect ExtractionOpinion MiningPrompt LearningSentiment Analysis+2Defending Deep Neural Networks against Backdoor Attacks via Module Switching
The exponential increase in the parameters of Deep Neural Networks (DNNs) has significantly raised the cost of independent training, particularly for resource-constrained entities. As a result, there is a growing relianc…
Evolutionary AlgorithmsSST-2Enhancing 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-2Catastrophic Forgetting in LLMs: A Comparative Analysis Across Language Tasks
Large Language Models (LLMs) have significantly advanced Natural Language Processing (NLP), particularly in Natural Language Understanding (NLU) tasks. As we progress toward an agentic world where LLM-based agents autono…
CoLAContinual LearningMRPCNatural Language Understanding+2An End-to-End Homomorphically Encrypted Neural Network
Every commercially available, state-of-the-art neural network consume plain input data, which is a well-known privacy concern. We propose a new architecture based on homomorphic encryption, which allows the neural networ…
Sentiment AnalysisSST-2Exploring Variability in Fine-Tuned Models for Text Classification with DistilBERT
This study evaluates fine-tuning strategies for text classification using the DistilBERT model, specifically the distilbert-base-uncased-finetuned-sst-2-english variant. Through structured experiments, we examine the inf…
regressionSST-2text-classificationText ClassificationCut the Deadwood Out: Post-Training Model Purification with Selective Module Substitution
The success of DNNs often depends on training with large-scale datasets, but building such datasets is both expensive and challenging. Consequently, public datasets from open-source platforms like HuggingFace have become…
Data PoisoningSST-2Contextual Feedback Loops: Amplifying Deep Reasoning with Iterative Top-Down Feedback
Conventional deep networks rely on one-way backpropagation that overlooks reconciling high-level predictions with lower-level representations. We propose \emph{Contextual Feedback Loops} (CFLs), a lightweight mechanism t…
SST-2Robustness of Large Language Models Against Adversarial Attacks
The increasing deployment of Large Language Models (LLMs) in various applications necessitates a rigorous evaluation of their robustness against adversarial attacks. In this paper, we present a comprehensive study on the…
Sentiment AnalysisSentiment ClassificationSST-2Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
Backdoor attacks covertly implant triggers into deep neural networks (DNNs) by poisoning a small portion of the training data with pre-designed backdoor triggers. This vulnerability is exacerbated in the era of large mod…
backdoor defenseModel EditingSST-2Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models
Fine-tuning is powerful for adapting large language models to downstream tasks, but it often results in huge memory usages. A promising approach to mitigate this is using Zeroth-Order (ZO) optimization, which estimates g…
SST-2Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition
Automated mechanistic interpretation research has attracted great interest due to its potential to scale explanations of neural network internals to large models. Existing automated circuit discovery work relies on activ…
Computational EfficiencySST-2SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN
Spiking neural network (SNN) has attracted great attention due to its characteristic of high efficiency and accuracy. Currently, the ANN-to-SNN conversion methods can obtain ANN on-par accuracy SNN with ultra-low latency…
AllSST-2LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
Differentially Private Stochastic Gradient Descent (DP-SGD) and its variants have been proposed to ensure rigorous privacy for fine-tuning large-scale pre-trained language models. However, they rely heavily on the Gaussi…
Language ModellingSST-2Text GenerationRevisiting Character-level Adversarial Attacks for Language Models
Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering senten…
Adversarial AttackSentenceSST-2LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactor…
Data AugmentationGSM8KSST-2The Impact of Quantization on the Robustness of Transformer-based Text Classifiers
Transformer-based models have made remarkable advancements in various NLP areas. Nevertheless, these models often exhibit vulnerabilities when confronted with adversarial attacks. In this paper, we explore the effect of …
QuantizationSST-2text-classificationText ClassificationHere'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-2When does word order matter and when doesn't it?
Language models (LMs) may appear insensitive to word order changes in natural language understanding (NLU) tasks. In this paper, we propose that linguistic redundancy can explain this phenomenon, whereby word order and o…
Natural Language UnderstandingRTESST-2