English
Related papers

Related papers: Towards Context-Invariant Safety Alignment for Lar…

200 papers

Finding the best way of adapting pre-trained language models to a task is a big challenge in current NLP. Just like the previous generation of task-tuned models (TT), models that are adapted to tasks via in-context-learning (ICL) are robust…

Computation and Language · Computer Science 2023-10-23 Lucas Weber , Elia Bruni , Dieuwke Hupkes

We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is generally costly and unstable to fine-tune large foundation…

Machine Learning · Computer Science 2024-10-17 Rui Yang , Xiaoman Pan , Feng Luo , Shuang Qiu , Han Zhong , Dong Yu , Jianshu Chen

Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar…

Computation and Language · Computer Science 2025-08-11 Sayantan Adak , Pratyush Chatterjee , Somnath Banerjee , Rima Hazra , Somak Aditya , Animesh Mukherjee

While LLMs demonstrate strong reasoning capabilities when provided with full information in a single turn, they exhibit substantial vulnerability in multi-turn interactions. Specifically, when information is revealed incrementally or…

Artificial Intelligence · Computer Science 2026-05-12 Xingwu Chen , Zhanqiu Zhang , Yiwen Guo , Difan Zou

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…

Computation and Language · Computer Science 2026-05-12 Jyotin Goel , Souvik Maji , Pratik Mazumder

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Computation and Language · Computer Science 2025-10-08 Kehua Feng , Keyan Ding , Yuhao Wang , Menghan Li , Fanjunduo Wei , Xinda Wang , Qiang Zhang , Huajun Chen

Finding appropriate prompts for the specific task has become an important issue as the usage of Large Language Models (LLM) has expanded. Reinforcement Learning (RL) is widely used for prompt tuning, but its inherent instability and…

Computation and Language · Computer Science 2024-10-11 Minchan Kwon , Gaeun Kim , Jongsuk Kim , Haeil Lee , Junmo Kim

With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignment methods based on instruction fine-tuning and…

Computation and Language · Computer Science 2025-12-16 Xiaoyun Zhang , Zhengyue Zhao , Wenxuan Shi , Kaidi Xu , Di Huang , Xing Hu

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal…

Machine Learning · Computer Science 2026-03-17 Ming Wen , Kun Yang , Xin Chen , Jingyu Zhang , Dingding Han , Shiwen Cui , Yuedong Xu

Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this…

Computation and Language · Computer Science 2025-05-27 Di Wu , Xin Lu , Yanyan Zhao , Bing Qin

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

Computation and Language · Computer Science 2026-03-23 Zafir Shamsi , Nikhil Chekuru , Zachary Guzman , Shivank Garg

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

Machine Learning · Computer Science 2025-10-21 Archie Chaudhury

Safety alignment for large language models (LLMs) aims to reduce harmful or unsafe behavior while preserving general utility. However, recent findings reveal that alignment effects can be fragile: lightweight post-alignment manipulations,…

Artificial Intelligence · Computer Science 2026-05-29 Zhihao Liu , Yifan Wu , Jian Lou , Di Wang , Yuxi Zhou , Yuke Hu

Large Language Model (LLM) agents are increasingly deployed in practice across a wide range of autonomous applications. Yet current safety mechanisms for LLM agents focus almost exclusively on preventing failures in advance, providing…

Artificial Intelligence · Computer Science 2026-02-13 Zibo Xiao , Jun Sun , Junjie Chen

Accurate uncertainty quantification is crucial for the safe deployment of machine learning models, and prior research has demonstrated improvements in the calibration of modern language models (LMs). We study in-context learning (ICL), a…

Computation and Language · Computer Science 2024-03-29 Hanlin Zhang , Yi-Fan Zhang , Yaodong Yu , Dhruv Madeka , Dean Foster , Eric Xing , Himabindu Lakkaraju , Sham Kakade

Safely aligning large language models (LLMs) often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on…

Cryptography and Security · Computer Science 2025-06-13 Kyubyung Chae , Hyunbin Jin , Taesup Kim

We introduce a multi-turn benchmark for evaluating personalised alignment in LLM-based AI assistants, focusing on their ability to handle user-provided safety-critical contexts. Our assessment of ten leading models across five scenarios…

Human-Computer Interaction · Computer Science 2025-01-31 Lize Alberts , Benjamin Ellis , Andrei Lupu , Jakob Foerster

The safety alignment of large language models (LLMs) remains vulnerable, as their initial behavior can be easily jailbroken by even relatively simple attacks. Since infilling a fixed template between the input instruction and initial model…

Computation and Language · Computer Science 2025-06-05 Chak Tou Leong , Qingyu Yin , Jian Wang , Wenjie Li

The success of AI assistants based on Language Models (LLMs) hinges on Reinforcement Learning from Human Feedback (RLHF) to comprehend and align with user intentions. However, traditional alignment algorithms, such as PPO, are hampered by…

Computation and Language · Computer Science 2024-07-03 Songyang Gao , Qiming Ge , Wei Shen , Shihan Dou , Junjie Ye , Xiao Wang , Rui Zheng , Yicheng Zou , Zhi Chen , Hang Yan , Qi Zhang , Dahua Lin

Two lines of work are taking the central stage in AI research. On the one hand, the community is making increasing efforts to build models that discard spurious correlations and generalize better in novel test environments. Unfortunately,…

Machine Learning · Computer Science 2023-09-21 Sharut Gupta , Stefanie Jegelka , David Lopez-Paz , Kartik Ahuja