English
Related papers

Related papers: POROver: Improving Safety and Reducing Overrefusal…

200 papers

Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Preeti Lamba , Kiran Ravish , Ankita Kushwaha , Pawan Kumar

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse propensity scoring to…

Machine Learning · Computer Science 2024-08-08 Shashank Gupta , Harrie Oosterhuis , Maarten de Rijke

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

Computation and Language · Computer Science 2024-01-01 Yaru Hao , Zewen Chi , Li Dong , Furu Wei

Video generation models have achieved remarkable progress in text-to-video tasks. These models are typically trained on text-video pairs with highly detailed and carefully crafted descriptions, while real-world user inputs during inference…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Jiale Cheng , Ruiliang Lyu , Xiaotao Gu , Xiao Liu , Jiazheng Xu , Yida Lu , Jiayan Teng , Zhuoyi Yang , Yuxiao Dong , Jie Tang , Hongning Wang , Minlie Huang

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Zhenhan Huang , Tejaswini Pedapati , Pin-Yu Chen , Jianxi Gao

We investigate a failure mode of large language models (LLMs) in which plain-text prompts elicit excessive outputs, a phenomenon we term Overflow. Unlike jailbreaks or prompt injection, Overflow arises under ordinary interaction settings…

Computation and Language · Computer Science 2026-01-14 Erin Feiglin , Nir Hutnik , Raz Lapid

Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating…

Computation and Language · Computer Science 2025-08-29 Hua Farn , Hsuan Su , Shachi H Kumar , Saurav Sahay , Shang-Tse Chen , Hung-yi Lee

It has been shown for English that discrete and soft prompting perform strongly in few-shot learning with pretrained language models (PLMs). In this paper, we show that discrete and soft prompting perform better than finetuning in…

Computation and Language · Computer Science 2021-09-09 Mengjie Zhao , Hinrich Schütze

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards only assess final answers, they also reward spurious…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Zhou Yu , Ziji Zhang , Hao Chen , Narayanan Sadagopan , Jing Huang , Tong Zhang , Anurag Beniwal

Large language models often lose previously aligned safety behaviors when fine-tuned on benign data, a phenomenon known as catastrophic forgetting. Prior work shows that adding random safety examples can mitigate this effect, but it remains…

Computation and Language · Computer Science 2025-10-28 Anh Pham , Mihir Thalanki , Michael Sun , Aditya Chaloo , Ankita Gupta , Tian Xia , Aditya Mate , Ehimwenma Nosakhare , Soundararajan Srinivasan

Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses. However, the performance of preference alignment is highly sensitive to the prevalent noise in the preference data.…

Machine Learning · Computer Science 2024-05-29 Xize Liang , Chao Chen , Shuang Qiu , Jie Wang , Yue Wu , Zhihang Fu , Zhihao Shi , Feng Wu , Jieping Ye

Soft prompt tuning techniques have recently gained traction as an effective strategy for the parameter-efficient tuning of pretrained language models, particularly minimizing the required adjustment of model parameters. Despite their…

Computation and Language · Computer Science 2024-06-11 MohammadAli SadraeiJavaeri , Ehsaneddin Asgari , Alice Carolyn McHardy , Hamid Reza Rabiee

Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven…

Sound · Computer Science 2025-11-18 Junan Zhang , Xueyao Zhang , Jing Yang , Yuancheng Wang , Fan Fan , Zhizheng Wu

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…

Machine Learning · Computer Science 2025-12-08 Mahesh Kumar Nandwana , Youngwan Lim , Joseph Liu , Alex Yang , Varun Notibala , Nishchaie Khanna

Multimodal large language models (MLLMs) hold considerable promise for applications in healthcare. However, their deployment in safety-critical settings is hindered by two key limitations: (i) sensitivity to prompt design, and (ii) a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Anita Kriz , Elizabeth Laura Janes , Xing Shen , Tal Arbel

Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study…

Computation and Language · Computer Science 2026-02-17 Jan Philip Wahle , Terry Ruas , Yang Xu , Bela Gipp

As large language models (LLMs) are increasingly applied across various domains, enhancing safety while maintaining the helpfulness of LLMs has become a critical challenge. Recent studies solve this problem through safety-constrained online…

Computation and Language · Computer Science 2025-06-04 Yupeng Qi , Ziyu Lyu , Min Yang , Yanlin Wang , Lu Bai , Lixin Cui

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Cryptography and Security · Computer Science 2024-08-23 Jayaram Raghuram , George Kesidis , David J. Miller

Instruction-fine-tuned large language models (LLMs) under 14B parameters continue to underperform on natural language understanding (NLU) tasks, often trailing smaller models like BERT-base on benchmarks such as GLUE and SuperGLUE.…

Computation and Language · Computer Science 2025-09-29 Bokai Hu , Sai Ashish Somayajula , Xin Pan , Pengtao Xie

Parameter-Efficient Fine-Tuning (PEFT) is widely used for adapting Large Language Models (LLMs) for various tasks. Recently, there has been an increasing demand for fine-tuning a single LLM for multiple tasks because it requires overall…

Computation and Language · Computer Science 2026-05-15 Anjir Ahmed Chowdhury , Syed Zawad , Xiaolong Ma , Xu Dong , Feng Yan