Image de couverture de livre

Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zheng, Aaron, Rana, Mansi, Stolcke, Andreas
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fine-tuning the SwissBERT Encoder Model for Embedding Sentences and Documents
par: Grosjean, Juri, et autres
Publié: (2024)

A Lightweight Explainable Guardrail for Prompt Safety
par: Islam, Md Asiful, et autres
Publié: (2026)

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
par: Hsiung, Lei, et autres
Publié: (2025)

REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models
par: Gupta, Ambuje, et autres
Publié: (2024)

Memorization of Named Entities in Fine-tuned BERT Models
par: Diera, Andor, et autres
Publié: (2022)

ACL: Aligned Contrastive Learning Improves BERT and Multi-exit BERT Fine-tuning
par: Li, Liz, et autres
Publié: (2026)

Detecting Bias in Large Language Models: Fine-tuned KcBERT
par: Lee, J. K., et autres
Publié: (2024)

Bypassing Safety Guardrails in LLMs Using Humor
par: Cisneros-Velarde, Pedro
Publié: (2025)

Fine-tuning BERT with Bidirectional LSTM for Fine-grained Movie Reviews Sentiment Analysis
par: Nkhata, Gibson, et autres
Publié: (2025)

Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training
par: Ilin, Aleksei, et autres
Publié: (2025)

Improving Sampling Methods for Fine-tuning SentenceBERT in Text Streams
par: Garcia, Cristiano Mesquita, et autres
Publié: (2024)

Question-Answering System for Bangla: Fine-tuning BERT-Bangla for a Closed Domain
par: Roy, Subal Chandra, et autres
Publié: (2024)

Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning
par: Ukarapol, Trapoom, et autres
Publié: (2024)

Few Dimensions are Enough: Fine-tuning BERT with Selected Dimensions Revealed Its Redundant Nature
par: Fukuhata, Shion, et autres
Publié: (2025)

Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
par: Huang, Tiansheng, et autres
Publié: (2025)

Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?
par: Hościłowicz, Jakub, et autres
Publié: (2023)

Biomedical Entity Linking for Dutch: Fine-tuning a Self-alignment BERT Model on an Automatically Generated Wikipedia Corpus
par: Hartendorp, Fons, et autres
Publié: (2024)

Slot Filling as a Reasoning Task for SpeechLLMs
par: Hacioglu, Kadri, et autres
Publié: (2025)

Bag of Tricks for Subverting Reasoning-based Safety Guardrails
par: Chen, Shuo, et autres
Publié: (2025)

ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
par: Wang, Yan, et autres
Publié: (2026)

MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety
par: Yang, Yahan, et autres
Publié: (2025)

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety
par: Zhang, Yuyou, et autres
Publié: (2025)

InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline
par: Kugler, Kai, et autres
Publié: (2021)

CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
par: An, Heajun, et autres
Publié: (2026)

Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models
par: Sreedhar, Makesh Narsimhan, et autres
Publié: (2025)

Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering
par: Chiniya, Purva, et autres
Publié: (2026)

CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual Signals
par: Novotney, Scott, et autres
Publié: (2022)

What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
par: Jain, Samyak, et autres
Publié: (2024)

Harnessing Large Language Models: Fine-tuned BERT for Detecting Charismatic Leadership Tactics in Natural Language
par: Saeid, Yasser, et autres
Publié: (2024)

PARA: Parameter-Efficient Fine-tuning with Prompt Aware Representation Adjustment
par: Liu, Zequan, et autres
Publié: (2025)

ColBERT: Using BERT Sentence Embedding in Parallel Neural Networks for Computational Humor
par: Annamoradnejad, Issa, et autres
Publié: (2020)

Why Do Safety Guardrails Degrade Across Languages?
par: Zhang, Max, et autres
Publié: (2026)

SpeechLLMs for Large-scale Contextualized Zero-shot Slot Filling
par: Hacioglu, Kadri, et autres
Publié: (2025)

iBERT: Interpretable Embeddings via Sense Decomposition
par: Anand, Vishal, et autres
Publié: (2025)

Topic mining based on fine-tuning Sentence-BERT and LDA
par: Li, Jianheng, et autres
Publié: (2025)

CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling
par: Fang, Zheng, et autres
Publié: (2023)

Zero-shot Slot Filling in the Age of LLMs for Dialogue Systems
par: Rana, Mansi, et autres
Publié: (2024)

Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety
par: Huang, Wei-Chieh, et autres
Publié: (2025)

GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning
par: Solatorio, Aivin V.
Publié: (2024)

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning
par: Wang, Guoli, et autres
Publié: (2026)