Image de couverture de livre

The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shen, Lingfeng, Tan, Weiting, Chen, Sihao, Chen, Yunmo, Zhang, Jingyu, Xu, Haoran, Zheng, Boyuan, Koehn, Philipp, Khashabi, Daniel
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
par: Tan, Weiting, et autres
Publié: (2024)

Streaming Sequence Transduction through Dynamic Compression
par: Tan, Weiting, et autres
Publié: (2024)

Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
par: Li, Tianjian, et autres
Publié: (2023)

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
par: Xu, Haoran, et autres
Publié: (2024)

Do pretrained Transformers Learn In-Context by Gradient Descent?
par: Shen, Lingfeng, et autres
Publié: (2023)

Learn and Unlearn: Addressing Misinformation in Multilingual LLMs
par: Lu, Taiming, et autres
Publié: (2024)

Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets
par: Li, Tianjian, et autres
Publié: (2024)

Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation
par: Tan, Weiting, et autres
Publié: (2025)

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
par: Zhang, Jingyu, et autres
Publié: (2024)

The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure
par: Bafna, Niyati, et autres
Publié: (2025)

GOLD PANNING: Strategic Context Shuffling for Needle-in-Haystack Reasoning
par: Byerly, Adam, et autres
Publié: (2025)

Challenging the Evaluator: LLM Sycophancy Under User Rebuttal
par: Kim, Sungwon, et autres
Publié: (2025)

Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems
par: Byerly, Adam, et autres
Publié: (2024)

It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF
par: Lu, Taiming, et autres
Publié: (2024)

Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents
par: Tan, Weiting, et autres
Publié: (2025)

Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data
par: Zhang, Jingyu, et autres
Publié: (2024)

SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning
par: Li, Tianjian, et autres
Publié: (2025)

Text Style Transfer with Parameter-efficient LLM Finetuning and Round-trip Translation
par: Liu, Ruoxi, et autres
Publié: (2026)

Speech Vecalign: an Embedding-based Method for Aligning Parallel Speech Documents
par: Meng, Chutong, et autres
Publié: (2025)

Learning to Retrieve Iteratively for In-Context Learning
par: Chen, Yunmo, et autres
Publié: (2024)

Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation
par: Wang, Hexuan, et autres
Publié: (2026)

Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations
par: Chen, Nuo, et autres
Publié: (2023)

Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG
par: Ki, Dayeon, et autres
Publié: (2025)

SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses
par: Jiang, Dongwei, et autres
Publié: (2024)

X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
par: Xu, Haoran, et autres
Publié: (2024)

Dissecting Multiplication in Transformers: Insights into LLMs
par: Qiu, Luyu, et autres
Publié: (2024)

MultiMUC: Multilingual Template Filling on MUC-4
par: Gantt, William, et autres
Publié: (2024)

Certified Mitigation of Worst-Case LLM Copyright Infringement
par: Zhang, Jingyu, et autres
Publié: (2025)

Jailbreak Distillation: Renewable Safety Benchmarking
par: Zhang, Jingyu, et autres
Publié: (2025)

Pointer-Generator Networks for Low-Resource Machine Translation: Don't Copy That!
par: Bafna, Niyati, et autres
Publié: (2024)

Recovering document annotations for sentence-level bitext
par: Wicks, Rachel, et autres
Publié: (2024)

SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation
par: Hou, Abe Bohan, et autres
Publié: (2023)

The Alignment Waltz: Jointly Training Agents to Collaborate for Safety
par: Zhang, Jingyu, et autres
Publié: (2025)

ICL CIPHERS: Quantifying "Learning" in In-Context Learning via Substitution Ciphers
par: Fang, Zhouxiang, et autres
Publié: (2025)

Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback
par: Jiang, Dongwei, et autres
Publié: (2025)

Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell
par: Lu, Taiming, et autres
Publié: (2024)

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
par: Wang, Mingyang, et autres
Publié: (2025)

All Languages Matter: On the Multilingual Safety of Large Language Models
par: Wang, Wenxuan, et autres
Publié: (2023)

Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models
par: Lian, Haoran, et autres
Publié: (2024)

LongSafety: Enhance Safety for Long-Context LLMs
par: Huang, Mianqiu, et autres
Publié: (2024)