English
Related papers

Related papers: Selective Safety Steering via Value-Filtered Decod…

200 papers

Recent advancements in large language models (LLMs) have enabled their widespread use across diverse real-world applications. However, concerns remain about their tendency to encode and reproduce ideological biases along political and…

Computation and Language · Computer Science 2025-09-23 Afrozah Nadeem , Mark Dras , Usman Naseem

Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual-textual understanding, yet their reliability is critically undermined by hallucinations, i.e., the generation of factually incorrect or inconsistent responses.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Chengsheng Zhang , Chenghao Sun , Xinyan Jiang , Wei Li , Xinmei Tian

Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and…

Computation and Language · Computer Science 2024-10-29 Rima Hazra , Sayan Layek , Somnath Banerjee , Soujanya Poria

Solving complex, long-horizon robotic manipulation tasks requires a deep understanding of physical interactions, reasoning about their long-term consequences, and precise high-level planning. Vision-Language Models (VLMs) offer a general…

Robotics · Computer Science 2026-02-24 Yanting Yang , Shenyuan Gao , Qingwen Bu , Li Chen , Dimitris N. Metaxas

Constrained decoding approaches aim to control the meaning or style of text generated by the pre-trained large language models (LLMs or also PLMs) for various tasks at inference time. However, these methods often guide plausible…

Computation and Language · Computer Science 2025-05-06 Chen Xu , Tian Lan , Yu Ji , Changlong Yu , Wei Wang , Jun Gao , Qunxi Dong , Kun Qian , Piji Li , Wei Bi , Bin Hu

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

Machine Learning · Computer Science 2026-01-07 Tuc Nguyen , Thai Le

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

Computation and Language · Computer Science 2024-07-31 Yuanpu Cao , Tianrong Zhang , Bochuan Cao , Ziyi Yin , Lu Lin , Fenglong Ma , Jinghui Chen

Frontier Large Language Models (LLMs) can be socially discriminatory or sensitive to spurious features of their inputs. Because only well-resourced corporations can train frontier LLMs, we need robust test-time strategies to control such…

Computation and Language · Computer Science 2024-10-08 Leonardo Cotta , Chris J. Maddison

With the rapid advancement of test-time compute search strategies to improve the mathematical problem-solving capabilities of large language models (LLMs), the need for building robust verifiers has become increasingly important. However,…

Computation and Language · Computer Science 2025-03-11 Jung Hyun Lee , June Yong Yang , Byeongho Heo , Dongyoon Han , Kyungsu Kim , Eunho Yang , Kang Min Yoo

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

Computation and Language · Computer Science 2023-10-10 Yi Dong , Zhilin Wang , Makesh Narsimhan Sreedhar , Xianchao Wu , Oleksii Kuchaiev

How can small-scale large language models (LLMs) efficiently utilize the supervision of LLMs to improve their generative quality? This question has been well studied in scenarios where there is no restriction on the number of LLM…

Computation and Language · Computer Science 2024-10-04 Hyunjong Ok , Jegwang Ryu , Jaeho Lee

Decoding strategies for generative large language models (LLMs) are a critical but often underexplored aspect of text generation tasks. Guided by specific hyperparameters, these strategies aim to transform the raw probability distributions…

Computation and Language · Computer Science 2024-12-17 Esteban Garces Arias , Meimingwei Li , Christian Heumann , Matthias Aßenmacher

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in…

Computation and Language · Computer Science 2024-01-23 Pengyu Wang , Dong Zhang , Linyang Li , Chenkun Tan , Xinghao Wang , Ke Ren , Botian Jiang , Xipeng Qiu

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Artificial Intelligence · Computer Science 2026-02-03 Sicheng Shen , Mingyang Lv , Han Shen , Jialin Wu , Binghao Wang , Zhou Yang , Guobin Shen , Dongcheng Zhao , Feifei Zhao , Yi Zeng

Test-time scaling (TTS) has emerged as a new frontier for scaling the performance of Large Language Models. In test-time scaling, by using more computational resources during inference, LLMs can improve their reasoning process and task…

Computation and Language · Computer Science 2025-09-10 V Venktesh , Mandeep Rathee , Avishek Anand

Ensuring safe and appropriate responses from vision-language models (VLMs) remains a critical challenge, particularly in high-risk or ambiguous scenarios. We introduce SafeCoT, a lightweight, interpretable framework that leverages…

Artificial Intelligence · Computer Science 2025-06-12 Jiachen Ma , Zhanhui Zhou , Chao Yang , Chaochao Lu

Aligning Large Language Models (LLMs) with human preferences is critical, yet traditional fine-tuning methods are computationally expensive and inflexible. While test-time alignment offers a promising alternative, existing approaches often…

Artificial Intelligence · Computer Science 2026-01-16 Tiesunlong Shen , Rui Mao , Jin Wang , Heming Sun , Jian Zhang , Xuejie Zhang , Erik Cambria

Vision-language models (VLMs) often inherit the biases and unsafe associations present within their large-scale training dataset. While recent approaches mitigate unsafe behaviors, their evaluation focuses on how safe the model is on unsafe…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Moreno D'Incà , Elia Peruzzo , Xingqian Xu , Humphrey Shi , Nicu Sebe , Massimiliano Mancini

Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Walter Gerych , Haoran Zhang , Kimia Hamidieh , Eileen Pan , Maanas Sharma , Thomas Hartvigsen , Marzyeh Ghassemi