English
Related papers

Related papers: POROver: Improving Safety and Reducing Overrefusal…

200 papers

As vision-language models (VLMs) become increasingly capable, maintaining a balance between safety and usefulness remains a central challenge. Safety mechanisms, while essential, can backfire, causing over-refusal, where models decline…

Computation and Language · Computer Science 2026-03-20 Kaixuan Ren , Preslav Nakov , Usman Naseem

Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This risk motivates safety efforts such as red-teaming and large-scale feedback learning, which aim to make models both…

Computation and Language · Computer Science 2024-04-02 Paul Röttger , Hannah Rose Kirk , Bertie Vidgen , Giuseppe Attanasio , Federico Bianchi , Dirk Hovy

Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors. To study these risks, researchers develop model organisms: models finetuned to exhibit specific known behaviors…

Computation and Language · Computer Science 2026-05-05 Mohammed Abu Baker , Luca Baroni , Dan Wilhelm

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Computation and Language · Computer Science 2024-08-30 Tian Ye , Zicheng Xu , Yuanzhi Li , Zeyuan Allen-Zhu

Prompt tuning has become a new paradigm for model tuning and it has demonstrated success in natural language pretraining and even vision pretraining. In this work, we explore the transfer of prompt tuning to multimodal pretraining, with a…

Computation and Language · Computer Science 2022-08-05 Hao Yang , Junyang Lin , An Yang , Peng Wang , Chang Zhou , Hongxia Yang

While fusing the capacities and advantages of various large language models offers a pathway to construct more powerful and versatile models, a fundamental challenge is to properly select advantageous model during training. Existing fusion…

Computation and Language · Computer Science 2025-11-18 Tianyuan Shi , Fanqi Wan , Canbin Huang , Xiaojun Quan , Chenliang Li , Ming Yan , Ji Zhang , Minhua Huang , Wu Kai

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Computation and Language · Computer Science 2024-09-04 Bocheng Chen , Hanqing Guo , Guangjing Wang , Yuanda Wang , Qiben Yan

Self-play preference optimization has emerged as a prominent paradigm for aligning large language models (LLMs). It typically involves a language model to generate on-policy responses for prompts and a reward model (RM) to guide the…

Computation and Language · Computer Science 2026-03-03 Yao Xiao , Jung-jae Kim , Roy Ka-wei Lee , Lidong Bing

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Computation and Language · Computer Science 2023-08-28 Aibek Bekbayev , Sungbae Chun , Yerzat Dulat , James Yamazaki

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…

Machine Learning · Computer Science 2025-02-28 Xiyue Peng , Hengquan Guo , Jiawei Zhang , Dongqing Zou , Ziyu Shao , Honghao Wei , Xin Liu

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Computation and Language · Computer Science 2025-12-24 Xiang Chen , Yixin Ou , Quan Feng , Lei Li , Piji Li , Haibo Ye , Sheng-Jun Huang , Shuofei Qiao , Shumin Deng , Huajun Chen , Ningyu Zhang

Current instruction-tuned language models are exclusively trained with textual preference data and thus are often not aligned with the unique requirements of other modalities, such as speech. To better align language models with the speech…

We demonstrate that co-training (Blum & Mitchell, 1998) can improve the performance of prompt-based learning by using unlabeled data. While prompting has emerged as a promising paradigm for few-shot and zero-shot learning, it is often…

Computation and Language · Computer Science 2022-02-03 Hunter Lang , Monica Agrawal , Yoon Kim , David Sontag

Large language model performance can be improved in a large number of ways. Many such techniques, like fine-tuning or advanced tool usage, are time-intensive and expensive. Although prompt engineering is significantly cheaper and often…

Computation and Language · Computer Science 2025-06-03 Philipp Schoenegger , Cameron R. Jones , Philip E. Tetlock , Barbara Mellers

Large Language Models (LLMs) are prone to off-topic misuse, where users may prompt these models to perform tasks beyond their intended scope. Current guardrails, which often rely on curated examples or custom classifiers, suffer from high…

Computation and Language · Computer Science 2025-04-10 Gabriel Chua , Shing Yee Chan , Shaun Khoo

Adapting general-purpose language models to new skills is currently an expensive process that must be repeated as new instruction datasets targeting new skills are created, or can cause the models to forget older skills. In this work, we…

Computation and Language · Computer Science 2024-10-18 Jacob Morrison , Noah A. Smith , Hannaneh Hajishirzi , Pang Wei Koh , Jesse Dodge , Pradeep Dasigi

The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable outputs. While such…

Cryptography and Security · Computer Science 2024-07-19 Shuli Jiang , Swanand Ravindra Kadhe , Yi Zhou , Farhan Ahmed , Ling Cai , Nathalie Baracaldo

Prompt engineering has made significant contributions to the era of large language models, yet its effectiveness depends on the skills of a prompt author. This paper introduces $\textit{iPrOp}$, a novel interactive prompt optimization…

Computation and Language · Computer Science 2025-06-30 Jiahui Li , Roman Klinger

Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several safety-driving factors into one, obscuring the specific cause(s) of safety…

Computation and Language · Computer Science 2026-05-19 Max Zhang , Ameen Patel , Sang T. Truong , Sanmi Koyejo

Parameter efficient learning methods (PERMs) have recently gained significant attention as they provide an efficient way for pre-trained language models (PLMs) to adapt to a downstream task. However, these conclusions are mostly drawn from…

Computation and Language · Computer Science 2022-10-26 Peng Xu , Mostofa Patwary , Shrimai Prabhumoye , Virginia Adams , Ryan J. Prenger , Wei Ping , Nayeon Lee , Mohammad Shoeybi , Bryan Catanzaro
‹ Prev 1 3 4 5 6 7 10 Next ›