English
Related papers

Related papers: Narrow Fine-Tuning Erodes Safety Alignment in Visi…

200 papers

Numerous studies have shown that multimodal LLMs process speech and images well but fail in non-intuitive ways rendering trivial tasks such as object counting unreliable. We investigate this behavior from an information-theoretic…

Computation and Language · Computer Science 2026-03-09 Jayadev Billa

The rapid deployment of Large Language Models and AI agents across critical societal and technical domains is hindered by persistent behavioral pathologies including sycophancy, hallucination, and strategic deception that resist mitigation…

Artificial Intelligence · Computer Science 2026-02-23 Xingcheng Xu , Jingjing Qu , Qiaosheng Zhang , Chaochao Lu , Yanqing Yang , Na Zou , Xia Hu

Writing radiology reports from medical images requires a high level of domain expertise. It is time-consuming even for trained radiologists and can be error-prone for inexperienced radiologists. It would be appealing to automate this task…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Yuzhe Lu , Sungmin Hong , Yash Shah , Panpan Xu

This paper examines a critical yet unexplored dimension of the AI alignment problem: the potential for Large Language Models (LLMs) to inherit and amplify existing misalignments between human espoused theories and theories-in-use. Drawing…

Human-Computer Interaction · Computer Science 2025-07-04 Tim Rogers , Ben Teehankee

Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer from intertwined deficiencies: insufficient robustness…

Machine Learning · Computer Science 2025-08-14 Birong Pan , Mayi Xu , Qiankun Pi , Jianhao Chen , Yuanyuan Zhu , Ming Zhong , Tieyun Qian

The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-collisions, scenarios that are brief, rare, and difficult for generic vision models to capture.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Mohammad Qazim Bhat , Yufan Huang , Niket Agarwal , Hao Wang , Michael Woods , John Kenyon , Tsung-Yi Lin , Xiaodong Yang , Ming-Yu Liu , Kevin Xie

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom…

Computation and Language · Computer Science 2023-10-06 Xiangyu Qi , Yi Zeng , Tinghao Xie , Pin-Yu Chen , Ruoxi Jia , Prateek Mittal , Peter Henderson

Vision-Language Models (VLMs) have shown strong performance in tasks like visual question answering and multimodal text generation, but their effectiveness in scientific domains such as materials science remains limited. While some machine…

Machine Learning · Computer Science 2025-11-11 An Vuong , Minh-Hao Van , Prateek Verma , Chen Zhao , Xintao Wu

A key concern with the concept of "alignment" is the implicit question of "alignment to what?". AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. Additionally,…

Computation and Language · Computer Science 2024-07-09 Aakanksha , Arash Ahmadian , Beyza Ermis , Seraphina Goldfarb-Tarrant , Julia Kreutzer , Marzieh Fadaee , Sara Hooker

Current safety alignment for Large Language Models (LLMs) implicitly optimizes for a "modal adult user," leaving models vulnerable to distributional shifts in user cognition. We present ChildSafe, a benchmark that quantifies alignment…

Computers and Society · Computer Science 2026-01-21 Abhejay Murali , Saleh Afroogh , Kevin Chen , David Atkinson , Amit Dhurandhar , Junfeng Jiao

Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data…

Computation and Language · Computer Science 2024-12-12 Yuxiao Lu , Arunesh Sinha , Pradeep Varakantham

Fine-tuning large language models (LLMs) is a common practice to adapt generalist models to specialized domains. However, recent studies show that fine-tuning can erode safety alignment, causing LLMs to respond to harmful or unethical…

Computation and Language · Computer Science 2026-04-24 Aladin Djuhera , Swanand Ravindra Kadhe , Farhan Ahmed , Syed Zawad , Holger Boche

Instruction fine-tuning has emerged as a critical technique for customizing Large Language Models (LLMs) to specific applications. However, recent studies have highlighted significant security vulnerabilities in fine-tuned LLMs. Existing…

Computation and Language · Computer Science 2025-02-18 Yanrui Du , Sendong Zhao , Jiawei Cao , Ming Ma , Danyang Zhao , Shuren Qi , Fenglei Fan , Ting Liu , Bing Qin

Recent research demonstrates that the nascent fine-tuning-as-a-service business model exposes serious safety concerns: fine-tuning with a few harmful data uploaded from the users can compromise the safety alignment of the model. The attack,…

Cryptography and Security · Computer Science 2026-04-27 Tiansheng Huang , Sihao Hu , Fatih Ilhan , Selim Furkan Tekin , Ling Liu

Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Feng Han , Zhixiong Zhang , Zheming Liang , Yibin Wang , Jiaqi Wang

The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety…

Computation and Language · Computer Science 2025-06-10 Sooyung Choi , Jaehyeok Lee , Xiaoyuan Yi , Jing Yao , Xing Xie , JinYeong Bak

Behavioral alignment in large language models (LLMs) is often achieved through broad fine-tuning, which can result in undesired side effects like distributional shift and low interpretability. We propose a method for alignment that…

Machine Learning · Computer Science 2026-01-28 Claire O'Brien , Jessica Seto , Dristi Roy , Aditya Dwivedi , Sunishchal Dev , Kevin Zhu , Sean O'Brien , Ashwinee Panda , Ryan Lagasse

Fine-tuning large language models (LLMs) with high parameter efficiency for downstream tasks has become a new paradigm. Low-Rank Adaptation (LoRA) significantly reduces the number of trainable parameters for fine-tuning. Although it has…

Computation and Language · Computer Science 2024-08-14 Jia-Chen Zhang , Yu-Jie Xiong , He-Xi Qiu , Dong-Hai Zhu , Chun-Ming Xia

Multimodal large language models (MLLMs) exhibit a pronounced preference for textual inputs when processing vision-language data, limiting their ability to reason effectively from visual evidence. Unlike prior studies that attribute this…

Artificial Intelligence · Computer Science 2026-04-21 Xinhan Zheng , Huyu Wu , Xueting Wang , Duo Su , Haiyun Jiang

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Zhendong Liu , Yuanbi Nie , Yingshui Tan , Xiangyu Yue , Qiushi Cui , Chongjun Wang , Xiaoyong Zhu , Bo Zheng