Image de couverture de livre

Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fu, Yu, Li, Yufei, Xiao, Wen, Liu, Cong, Dong, Yue
Format:	Preprint
Publié:	2023
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

MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment
par: Li, Yufei, et autres
Publié: (2025)

Cross-Task Defense: Instruction-Tuning LLMs for Content Safety
par: Fu, Yu, et autres
Publié: (2024)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
par: Li, Hao, et autres
Publié: (2026)

The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs
par: Zhang, Xing, et autres
Publié: (2026)

NLP-ADBench: NLP Anomaly Detection Benchmark
par: Li, Yuangang, et autres
Publié: (2024)

Long Context Alignment with Short Instructions and Synthesized Positions
par: Wu, Wenhao, et autres
Publié: (2024)

AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference
par: Han, Yang, et autres
Publié: (2024)

LongAlign: A Recipe for Long Context Alignment of Large Language Models
par: Bai, Yushi, et autres
Publié: (2024)

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
par: Wang, Jiongxiao, et autres
Publié: (2024)

MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models
par: Xia, Yinan, et autres
Publié: (2025)

OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety
par: Liu, Chuang, et autres
Publié: (2024)

Improving Weak-to-Strong Generalization with Reliability-Aware Alignment
par: Guo, Yue, et autres
Publié: (2024)

Abstractive Text Summarization for Bangla Language Using NLP and Machine Learning Approaches
par: Miazee, Asif Ahammad, et autres
Publié: (2025)

STAIR: Improving Safety Alignment with Introspective Reasoning
par: Zhang, Yichi, et autres
Publié: (2025)

AraFinNLP 2024: The First Arabic Financial NLP Shared Task
par: Malaysha, Sanad, et autres
Publié: (2024)

W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search
par: Ding, Zhenyu, et autres
Publié: (2025)

IterAlign: Iterative Constitutional Alignment of Large Language Models
par: Chen, Xiusi, et autres
Publié: (2024)

TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment
par: Li, Chong, et autres
Publié: (2026)

Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
par: Zhu, Wenhong, et autres
Publié: (2024)

NLP Datasets for Idiom and Figurative Language Tasks
par: Matheny, Blake, et autres
Publié: (2025)

What Matters For Safety Alignment?
par: Li, Xing, et autres
Publié: (2026)

Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication
par: Eckman, Stephanie, et autres
Publié: (2025)

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
par: Huang, Caishuang, et autres
Publié: (2024)

AlignBench: Benchmarking Chinese Alignment of Large Language Models
par: Liu, Xiao, et autres
Publié: (2023)

Multi-Dimensional Evaluation of Text Summarization with In-Context Learning
par: Jain, Sameer, et autres
Publié: (2023)

Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
par: Bu, Yuyan, et autres
Publié: (2026)

Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks
par: Ham, Seokil, et autres
Publié: (2025)

Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models
par: Fu, Yu, et autres
Publié: (2025)

YaleNLP @ PerAnsSumm 2025: Multi-Perspective Integration via Mixture-of-Agents for Enhanced Healthcare QA Summarization
par: Jang, Dongsuk, et autres
Publié: (2025)

Personalized Abstractive Summarization by Tri-agent Generation Pipeline
par: Xiao, Wen, et autres
Publié: (2023)

HERA: Improving Long Document Summarization using Large Language Models with Context Packaging and Reordering
par: Li, Taiji, et autres
Publié: (2025)

Annotator-Centric Active Learning for Subjective NLP Tasks
par: van der Meer, Michiel, et autres
Publié: (2024)

How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment
par: Huang, Heyan, et autres
Publié: (2024)

On Context Utilization in Summarization with Large Language Models
par: Ravaut, Mathieu, et autres
Publié: (2023)

Comparative Evaluation of ChatGPT and DeepSeek Across Key NLP Tasks: Strengths, Weaknesses, and Domain-Specific Performance
par: Etaiwi, Wael, et autres
Publié: (2025)

Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization
par: Srivastava, Aseem, et autres
Publié: (2024)

Membership Inference Attacks Against In-Context Learning
par: Wen, Rui, et autres
Publié: (2024)

Benchmarking LLMs on the Semantic Overlap Summarization Task
par: Salvador, John, et autres
Publié: (2024)

Towards Context-Invariant Safety Alignment for Large Language Models
par: Wang, Yixu, et autres
Publié: (2026)

Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study
par: Li, Yufei, et autres
Publié: (2024)