Copertina

SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Banerjee, Somnath, Layek, Sayan, Tripathy, Soham, Kumar, Shanu, Mukherjee, Animesh, Hazra, Rima
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations
di: Banerjee, Somnath, et al.
Pubblicazione: (2025)

Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
di: Banerjee, Somnath, et al.
Pubblicazione: (2025)

ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models
di: Banerjee, Somnath, et al.
Pubblicazione: (2025)

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
di: Hazra, Rima, et al.
Pubblicazione: (2024)

How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries
di: Banerjee, Somnath, et al.
Pubblicazione: (2024)

Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages
di: Banerjee, Somnath, et al.
Pubblicazione: (2026)

Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context
di: Banerjee, Somnath, et al.
Pubblicazione: (2024)

MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
di: Adak, Sayantan, et al.
Pubblicazione: (2025)

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
di: Hazra, Rima, et al.
Pubblicazione: (2024)

Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
di: Banerjee, Somnath, et al.
Pubblicazione: (2024)

Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
di: Banerjee, Somnath, et al.
Pubblicazione: (2024)

AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models
di: Adak, Sayantan, et al.
Pubblicazione: (2025)

SafeMath: Inference-time Safety improves Math Accuracy
di: Basu, Sagnik, et al.
Pubblicazione: (2026)

SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems
di: Hazra, Rima, et al.
Pubblicazione: (2026)

Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations
di: Banerjee, Somnath, et al.
Pubblicazione: (2026)

Evaluating the Ebb and Flow: An In-depth Analysis of Question-Answering Trends across Diverse Platforms
di: Hazra, Rima, et al.
Pubblicazione: (2023)

DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem
di: Banerjee, Somnath, et al.
Pubblicazione: (2024)

Redefining Developer Assistance: Through Large Language Models in Software Ecosystem
di: Banerjee, Somnath, et al.
Pubblicazione: (2023)

Tutoring Large Language Models to be Domain-adaptive, Precise, and Safe
di: Banerjee, Somnath
Pubblicazione: (2026)

Duplicate Question Retrieval and Confirmation Time Prediction in Software Communities
di: Hazra, Rima, et al.
Pubblicazione: (2023)

From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents
di: Rasheed, Razeen A, et al.
Pubblicazione: (2026)

InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks
di: Banerjee, Somnath, et al.
Pubblicazione: (2024)

Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
di: Zhang, Xiaoyun, et al.
Pubblicazione: (2024)

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

Steering Multimodal Large Language Models Decoding for Context-Aware Safety
di: Liu, Zheyuan, et al.
Pubblicazione: (2025)

Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions
di: Sachdeva, Rachneet, et al.
Pubblicazione: (2025)

On Almost Surely Safe Alignment of Large Language Models at Inference-Time
di: Ji, Xiaotong, et al.
Pubblicazione: (2025)

SafeLawBench: Towards Safe Alignment of Large Language Models
di: Cao, Chuxue, et al.
Pubblicazione: (2025)

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
di: Lee, Seanie, et al.
Pubblicazione: (2025)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
di: Wang, Yanbo, et al.
Pubblicazione: (2026)

Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model
di: Wang, Siyin, et al.
Pubblicazione: (2024)

Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models
di: Quamar, Mohammad Atif, et al.
Pubblicazione: (2025)

Benchmarking Motivational Interviewing Competence of Large Language Models
di: Jha, Aishwariya, et al.
Pubblicazione: (2026)

AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models
di: Kang, Hankun, et al.
Pubblicazione: (2026)

SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
di: Li, Tianhao, et al.
Pubblicazione: (2024)

SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
di: Djuhera, Aladin, et al.
Pubblicazione: (2025)

READ: Reinforcement-based Adversarial Learning for Text Classification with Limited Labeled Data
di: Sharma, Rohit, et al.
Pubblicazione: (2025)

CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models
di: Khandelwal, Anant, et al.
Pubblicazione: (2025)

DeAL: Decoding-time Alignment for Large Language Models
di: Huang, James Y., et al.
Pubblicazione: (2024)

Exploring Safety-Utility Trade-Offs in Personalized Language Models
di: Vijjini, Anvesh Rao, et al.
Pubblicazione: (2024)