Copertina

Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Neill, James O', Subramanian, Santhosh, Lin, Eric, Mugunthan, Vaikkunth
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs
di: Manczak, Blazej, et al.
Pubblicazione: (2025)

PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing
di: Manczak, Blazej, et al.
Pubblicazione: (2024)

LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models
di: Elesedy, Hayder, et al.
Pubblicazione: (2024)

UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models
di: Oh, Sejoon, et al.
Pubblicazione: (2024)

Noise Injection Systemically Degrades Large Language Model Safety Guardrails
di: Shahani, Prithviraj Singh, et al.
Pubblicazione: (2025)

Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation
di: Gueorguieva, Anna-Maria, et al.
Pubblicazione: (2025)

Why Do Safety Guardrails Degrade Across Languages?
di: Zhang, Max, et al.
Pubblicazione: (2026)

DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models
di: Zhang, Yuxuan, et al.
Pubblicazione: (2024)

FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion
di: Tang, Anke, et al.
Pubblicazione: (2024)

Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?
di: Sun, Albert Yu, et al.
Pubblicazione: (2023)

Recurrent Knowledge Identification and Fusion for Language Model Continual Learning
di: Feng, Yujie, et al.
Pubblicazione: (2025)

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
di: Yuan, Zhuowen, et al.
Pubblicazione: (2024)

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
di: Krishna, Kundan, et al.
Pubblicazione: (2025)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
di: Oozeer, Narmeen, et al.
Pubblicazione: (2025)

CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants
di: Sun, Albert Yu, et al.
Pubblicazione: (2023)

SafePred: A Predictive Guardrail for Computer-Using Agents via World Models
di: Chen, Yurun, et al.
Pubblicazione: (2026)

Probabilistic Token Alignment for Large Language Model Fusion
di: Zeng, Runjia, et al.
Pubblicazione: (2025)

Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies
di: Song, Jingze, et al.
Pubblicazione: (2026)

Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
di: Huang, Tiansheng, et al.
Pubblicazione: (2025)

AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs
di: S, Santhosh G, et al.
Pubblicazione: (2025)

Language and Experience: A Computational Model of Social Learning in Complex Tasks
di: Colas, Cédric, et al.
Pubblicazione: (2025)

Evaluating Language-Model Agents on Realistic Autonomous Tasks
di: Kinniment, Megan, et al.
Pubblicazione: (2023)

Efficient Compositional Multi-tasking for On-device Large Language Models
di: Bohdal, Ondrej, et al.
Pubblicazione: (2025)

Knowledge Fusion of Large Language Models Via Modular SkillPacks
di: Du, Guodong, et al.
Pubblicazione: (2025)

MMSR: Symbolic Regression is a Multi-Modal Information Fusion Task
di: Li, Yanjie, et al.
Pubblicazione: (2024)

RadAnnotate: Large Language Models for Efficient and Reliable Radiology Report Annotation
di: Shetty, Saisha Pradeep, et al.
Pubblicazione: (2026)

Token-Efficient Leverage Learning in Large Language Models
di: Zeng, Yuanhao, et al.
Pubblicazione: (2024)

Pretrained Generative Language Models as General Learning Frameworks for Sequence-Based Tasks
di: Fauber, Ben
Pubblicazione: (2024)

Unified Representation of Genomic and Biomedical Concepts through Multi-Task, Multi-Source Contrastive Learning
di: Yuan, Hongyi, et al.
Pubblicazione: (2024)

Efficient Estimation of Kernel Surrogate Models for Task Attribution
di: Zhang, Zhenshuo, et al.
Pubblicazione: (2026)

OrchMoE: Efficient Multi-Adapter Learning with Task-Skill Synergy
di: Wang, Haowen, et al.
Pubblicazione: (2024)

A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models
di: Xie, Chengxing, et al.
Pubblicazione: (2024)

Learning to Model the World with Language
di: Lin, Jessy, et al.
Pubblicazione: (2023)

Learn To be Efficient: Build Structured Sparsity in Large Language Models
di: Zheng, Haizhong, et al.
Pubblicazione: (2024)

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
di: Hu, Mengkang, et al.
Pubblicazione: (2023)

DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression
di: Huang, Wei, et al.
Pubblicazione: (2025)

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
di: Zhao, Shiwan, et al.
Pubblicazione: (2026)

RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models
di: Chen, Shuhao, et al.
Pubblicazione: (2024)

Large Language Models as Generalizable Policies for Embodied Tasks
di: Szot, Andrew, et al.
Pubblicazione: (2023)

ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Tasks
di: Zhu, Yinghao, et al.
Pubblicazione: (2024)