Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fu, Yu, Li, Yufei, Xiao, Wen, Liu, Cong, Dong, Yue
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment
di: Li, Yufei, et al.
Pubblicazione: (2025)

Cross-Task Defense: Instruction-Tuning LLMs for Content Safety
di: Fu, Yu, et al.
Pubblicazione: (2024)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
di: Li, Hao, et al.
Pubblicazione: (2026)

The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs
di: Zhang, Xing, et al.
Pubblicazione: (2026)

NLP-ADBench: NLP Anomaly Detection Benchmark
di: Li, Yuangang, et al.
Pubblicazione: (2024)

Long Context Alignment with Short Instructions and Synthesized Positions
di: Wu, Wenhao, et al.
Pubblicazione: (2024)

AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference
di: Han, Yang, et al.
Pubblicazione: (2024)

LongAlign: A Recipe for Long Context Alignment of Large Language Models
di: Bai, Yushi, et al.
Pubblicazione: (2024)

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
di: Wang, Jiongxiao, et al.
Pubblicazione: (2024)

MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models
di: Xia, Yinan, et al.
Pubblicazione: (2025)

OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety
di: Liu, Chuang, et al.
Pubblicazione: (2024)

Improving Weak-to-Strong Generalization with Reliability-Aware Alignment
di: Guo, Yue, et al.
Pubblicazione: (2024)

Abstractive Text Summarization for Bangla Language Using NLP and Machine Learning Approaches
di: Miazee, Asif Ahammad, et al.
Pubblicazione: (2025)

STAIR: Improving Safety Alignment with Introspective Reasoning
di: Zhang, Yichi, et al.
Pubblicazione: (2025)

AraFinNLP 2024: The First Arabic Financial NLP Shared Task
di: Malaysha, Sanad, et al.
Pubblicazione: (2024)

W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search
di: Ding, Zhenyu, et al.
Pubblicazione: (2025)

IterAlign: Iterative Constitutional Alignment of Large Language Models
di: Chen, Xiusi, et al.
Pubblicazione: (2024)

TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment
di: Li, Chong, et al.
Pubblicazione: (2026)

Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
di: Zhu, Wenhong, et al.
Pubblicazione: (2024)

NLP Datasets for Idiom and Figurative Language Tasks
di: Matheny, Blake, et al.
Pubblicazione: (2025)

What Matters For Safety Alignment?
di: Li, Xing, et al.
Pubblicazione: (2026)

Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication
di: Eckman, Stephanie, et al.
Pubblicazione: (2025)

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
di: Huang, Caishuang, et al.
Pubblicazione: (2024)

AlignBench: Benchmarking Chinese Alignment of Large Language Models
di: Liu, Xiao, et al.
Pubblicazione: (2023)

Multi-Dimensional Evaluation of Text Summarization with In-Context Learning
di: Jain, Sameer, et al.
Pubblicazione: (2023)

Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
di: Bu, Yuyan, et al.
Pubblicazione: (2026)

Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks
di: Ham, Seokil, et al.
Pubblicazione: (2025)

Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models
di: Fu, Yu, et al.
Pubblicazione: (2025)

YaleNLP @ PerAnsSumm 2025: Multi-Perspective Integration via Mixture-of-Agents for Enhanced Healthcare QA Summarization
di: Jang, Dongsuk, et al.
Pubblicazione: (2025)

Personalized Abstractive Summarization by Tri-agent Generation Pipeline
di: Xiao, Wen, et al.
Pubblicazione: (2023)

HERA: Improving Long Document Summarization using Large Language Models with Context Packaging and Reordering
di: Li, Taiji, et al.
Pubblicazione: (2025)

Annotator-Centric Active Learning for Subjective NLP Tasks
di: van der Meer, Michiel, et al.
Pubblicazione: (2024)

How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment
di: Huang, Heyan, et al.
Pubblicazione: (2024)

On Context Utilization in Summarization with Large Language Models
di: Ravaut, Mathieu, et al.
Pubblicazione: (2023)

Comparative Evaluation of ChatGPT and DeepSeek Across Key NLP Tasks: Strengths, Weaknesses, and Domain-Specific Performance
di: Etaiwi, Wael, et al.
Pubblicazione: (2025)

Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization
di: Srivastava, Aseem, et al.
Pubblicazione: (2024)

Membership Inference Attacks Against In-Context Learning
di: Wen, Rui, et al.
Pubblicazione: (2024)

Benchmarking LLMs on the Semantic Overlap Summarization Task
di: Salvador, John, et al.
Pubblicazione: (2024)

Towards Context-Invariant Safety Alignment for Large Language Models
di: Wang, Yixu, et al.
Pubblicazione: (2026)

Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study
di: Li, Yufei, et al.
Pubblicazione: (2024)