English
Related papers

Related papers: Multilingual Safety Alignment via Self-Distillatio…

200 papers

Discrete diffusion models (DDMs) have shown powerful generation ability for discrete data modalities like text and molecules. However, their practical application is hindered by inefficient sampling, requiring a large number of sampling…

Machine Learning · Computer Science 2025-09-25 Feiyang Fu , Tongxian Guo , Zhaoqiang Liu

As the scale and complexity of jailbreaking attacks on large language models (LLMs) continue to escalate, their efficiency and practical applicability are constrained, posing a profound challenge to LLM security. Jailbreaking techniques…

Computation and Language · Computer Science 2025-12-23 Xiang Li , Chong Zhang , Jia Wang , Fangyu Wu , Yushi Li , Xiaobo Jin

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Computation and Language · Computer Science 2025-03-03 Samuele Poppi , Zheng-Xin Yong , Yifei He , Bobbie Chern , Han Zhao , Aobo Yang , Jianfeng Chi

Large language models (LLMs) deliver remarkable performance but are costly to deploy, motivating knowledge distillation (KD) for efficient inference. Existing KD objectives typically match student and teacher probabilities via softmax,…

Machine Learning · Computer Science 2026-03-03 Yeongmin Kim , Donghyeok Shin , Mina Kang , Byeonghu Na , Il-Chul Moon

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

Computation and Language · Computer Science 2025-09-29 Yahan Yang , Soham Dan , Shuo Li , Dan Roth , Insup Lee

Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a novel benchmark construction framework that "distills"…

Computation and Language · Computer Science 2025-05-29 Jingyu Zhang , Ahmed Elgohary , Xiawei Wang , A S M Iftekhar , Ahmed Magooda , Benjamin Van Durme , Daniel Khashabi , Kyle Jackson

Speech Large Language Models (LLMs) that understand and follow instructions in many languages are useful for real-world interaction, but are difficult to train with supervised fine-tuning, requiring large, task-specific speech corpora.…

Computation and Language · Computer Science 2026-03-10 Shreyas Gopal , Donghang Wu , Ashutosh Anshul , Yeo Yue Heng , Yizhou Peng , Haoyang Li , Hexin Liu , Eng Siong Chng

Multilingual semantic search is the task of retrieving relevant contents to a query expressed in different language combinations. This requires a better semantic understanding of the user's intent and its contextual meaning. Multilingual…

Computation and Language · Computer Science 2023-09-18 Meryem M'hamdi , Jonathan May , Franck Dernoncourt , Trung Bui , Seunghyun Yoon

LLMs have become a go-to solution not just for text generation, but also for natural language understanding (NLU) tasks. Acquiring extensive knowledge through language modeling on web-scale corpora, they excel on English NLU, yet struggle…

Computation and Language · Computer Science 2024-06-19 Fabian David Schmidt , Philipp Borchert , Ivan Vulić , Goran Glavaš

Diffusion Large Language Models (dLLMs) have recently emerged as a competitive non-autoregressive paradigm due to their unique training and inference approach. However, there is currently a lack of safety study on this novel architecture.…

Cryptography and Security · Computer Science 2025-11-27 Zhixin Xie , Xurui Song , Jun Luo

Large Language Models (LLMs) excel at various natural language processing tasks but remain vulnerable to jailbreaking attacks that induce harmful content generation. In this paper, we reveal a critical safety inconsistency: LLMs can more…

Computation and Language · Computer Science 2025-08-27 Peng Ding , Wen Sun , Dailin Li , Wei Zou , Jiaming Wang , Jiajun Chen , Shujian Huang

Massively multilingual Transformers (MMTs), such as mBERT and XLM-R, are widely used for cross-lingual transfer learning. While these are pretrained to represent hundreds of languages, end users of NLP systems are often interested only in…

Computation and Language · Computer Science 2023-06-05 Alan Ansell , Edoardo Maria Ponti , Anna Korhonen , Ivan Vulić

Truly multilingual safety moderation efforts for Large Language Models (LLMs) have been hindered by a narrow focus on a small set of languages (e.g., English, Chinese) as well as a limited scope of safety definition, resulting in…

Computation and Language · Computer Science 2025-08-08 Priyanshu Kumar , Devansh Jain , Akhila Yerukola , Liwei Jiang , Himanshu Beniwal , Thomas Hartvigsen , Maarten Sap

Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…

Computation and Language · Computer Science 2024-12-19 Tianyu Peng , Jiajun Zhang

Recent advances in LLMs have enhanced AI capabilities, but also increased the risk posed by malicious requests, highlighting the need for effective LLM safeguards to detect such queries. Existing approaches largely rely on classifier-based…

Computation and Language · Computer Science 2025-10-14 Zhuowei Chen , Bowei Zhang , Nankai Lin , Tian Hou , Lianxi Wang

Model extraction attacks (MEAs) on large language models (LLMs) have received increasing attention in recent research. However, existing attack methods typically adapt the extraction strategies originally developed for deep neural networks…

Cryptography and Security · Computer Science 2025-05-20 Zi Liang , Qingqing Ye , Yanyun Wang , Sen Zhang , Yaxin Xiao , Ronghua Li , Jianliang Xu , Haibo Hu

We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF). Our main idea is to exploit knowledge…

Computation and Language · Computer Science 2024-06-07 Haozheng Luo , Jiahao Yu , Wenxin Zhang , Jialong Li , Jerry Yao-Chieh Hu , Xinyu Xing , Han Liu

Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the…

Computation and Language · Computer Science 2024-10-02 Songming Zhang , Xue Zhang , Zengkui Sun , Yufeng Chen , Jinan Xu

Multilingual models have been widely used for cross-lingual transfer to low-resource languages. However, the performance on these languages is hindered by their underrepresentation in the pretraining data. To alleviate this problem, we…

Computation and Language · Computer Science 2023-05-29 Tomasz Limisiewicz , Dan Malkin , Gabriel Stanovsky

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…

Computation and Language · Computer Science 2025-05-30 Yi Luo , Zhenghao Lin , Yuhao Zhang , Jiashuo Sun , Chen Lin , Chengjin Xu , Xiangdong Su , Yelong Shen , Jian Guo , Yeyun Gong