English
Related papers

Related papers: POROver: Improving Safety and Reducing Overrefusal…

200 papers

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Prompt-based continual learning methods fine-tune only a small set of additional learnable parameters while keeping the pre-trained model's parameters frozen. It enables efficient adaptation to new tasks while mitigating the risk of…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Shengqin Jiang , Tianqi Kong , Yuankai Qi , Haokui Zhang , Lina Yao , Quan Z. Sheng , Qingshan Liu , Ming-Hsuan Yang

Parameter-efficient methods are able to use a single frozen pre-trained large language model (LLM) to perform many tasks by learning task-specific soft prompts that modulate model behavior when concatenated to the input text. However, these…

Computation and Language · Computer Science 2022-08-12 Brian Lester , Joshua Yurtsever , Siamak Shakeri , Noah Constant

While recent code-specific large language models (LLMs) have greatly enhanced their code generation capabilities, the safety of these models remains under-explored, posing potential risks as insecure code generated by these models may…

Cryptography and Security · Computer Science 2025-06-09 Xiangzhe Xu , Zian Su , Jinyao Guo , Kaiyuan Zhang , Zhenting Wang , Xiangyu Zhang

Many publicly available language models have been safety tuned to reduce the likelihood of toxic or liability-inducing text. To redteam or jailbreak these models for compliance with toxic requests, users and security analysts have developed…

Computation and Language · Computer Science 2024-10-02 T. Ben Thompson , Michael Sklar

We propose Consistency-guided Prompt learning (CoPrompt), a new fine-tuning method for vision-language models. Our approach improves the generalization of large foundation models when fine-tuned on downstream tasks in a few-shot setting.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Shuvendu Roy , Ali Etemad

Multitask prompted finetuning (MTF) has been shown to help large language models generalize to new tasks in a zero-shot setting, but so far explorations of MTF have focused on English data and models. We apply MTF to the pretrained…

Large language models are highly sensitive to prompt wording. However, popular automatic prompt search methods, including InstructZero, often degrade under distribution shift and adversarial evaluation because they optimize expected…

Machine Learning · Computer Science 2025-10-20 Yangyang Li

Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular community platforms now offer convenient distribution of a large…

Machine Learning · Computer Science 2024-09-02 Md Rafi Ur Rashid , Jing Liu , Toshiaki Koike-Akino , Shagufta Mehnaz , Ye Wang

Language model fine-tuning is essential for modern natural language processing, but is computationally expensive and time-consuming. Further, the effectiveness of fine-tuning is limited by the inclusion of training examples that negatively…

Computation and Language · Computer Science 2022-05-23 Richard Antonello , Nicole Beckage , Javier Turek , Alexander Huth

Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled…

Computation and Language · Computer Science 2026-03-26 Avni Mittal

Large Language Models (LLMs) increasingly exhibit over-refusal - erroneously rejecting benign queries due to overly conservative safety measures - a critical functional flaw that undermines their reliability and usability. Current methods…

Software Engineering · Computer Science 2026-05-05 Haonan Zhang , Dongxia Wang , Yi Liu , Kexin Chen , Jiashui Wang , Xinlei Ying , Long Liu , Wenhai Wang

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and…

Computation and Language · Computer Science 2026-04-21 Zhexin Zhang , Xian Qi Loye , Victor Shea-Jay Huang , Junxiao Yang , Qi Zhu , Shiyao Cui , Fei Mi , Lifeng Shang , Yingkang Wang , Hongning Wang , Minlie Huang

Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. However, ensuring their safe use remains a significant challenge. Preference training and safety measures often overfit to harms…

Computation and Language · Computer Science 2024-10-15 Aakanksha , Arash Ahmadian , Seraphina Goldfarb-Tarrant , Beyza Ermis , Marzieh Fadaee , Sara Hooker

Pretrained vision-language models (VLMs) such as CLIP have shown impressive generalization capability in downstream vision tasks with appropriate text prompts. Instead of designing prompts manually, Context Optimization (CoOp) has been…

Computer Vision and Pattern Recognition · Computer Science 2023-02-15 Chengcheng Ma , Yang Liu , Jiankang Deng , Lingxi Xie , Weiming Dong , Changsheng Xu

In prompt tuning, a prefix or suffix text is added to the prompt, and the embeddings (soft prompts) or token indices (hard prompts) of the prefix/suffix are optimized to gain more control over language models for specific tasks. This…

Computation and Language · Computer Science 2024-07-01 Shouchang Guo , Sonam Damani , Keng-hao Chang

Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns…

Computation and Language · Computer Science 2025-04-04 Nikhil Verma , Manasa Bharadwaj

The safety alignment of large language models (LLMs) is becoming increasingly important with their democratization. In this paper, we study the safety degradation that comes with adapting LLMs to new tasks. We attribute this safety…

Computation and Language · Computer Science 2025-12-12 Lama Alssum , Hani Itani , Hasan Abed Al Kader Hammoud , Philip Torr , Adel Bibi , Bernard Ghanem

In this paper, we conduct a thorough investigation into the reasoning capabilities of Large Language Models (LLMs), focusing specifically on the Open Pretrained Transformers (OPT) models as a representative of such models. Our study entails…

Computation and Language · Computer Science 2023-10-25 Badr AlKhamissi , Siddharth Verma , Ping Yu , Zhijing Jin , Asli Celikyilmaz , Mona Diab