English
Related papers

Related papers: RepIt: Steering Language Models with Concept-Speci…

200 papers

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse…

Computation and Language · Computer Science 2025-05-26 Youliang Yuan , Wenxiang Jiao , Wenxuan Wang , Jen-tse Huang , Jiahao Xu , Tian Liang , Pinjia He , Zhaopeng Tu

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

Cryptography and Security · Computer Science 2026-05-21 Junxi Chen , Junhao Dong , Xiaohua Xie

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

Machine Learning · Computer Science 2025-09-29 Sathwik Karnik , Somil Bansal

Protecting the intellectual property of large language models (LLMs) is a critical challenge due to the proliferation of unauthorized derivative models. We introduce a novel fingerprinting framework that leverages the behavioral patterns…

Cryptography and Security · Computer Science 2026-02-11 Zhenyu Xu , Victor S. Sheng

Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection (PI), where…

Cryptography and Security · Computer Science 2025-09-17 Mengxiao Wang , Yuxuan Zhang , Guofei Gu

Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject undetectable perturbations into the data during inference,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Shuhan Xu , Siyuan Liang , Hongling Zheng , Aishan Liu , Xinbiao Wang , Yong Luo , Fu Lin , Leszek Rutkowski , Dacheng Tao

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its…

Machine Learning · Computer Science 2024-11-01 Andy Arditi , Oscar Obeso , Aaquib Syed , Daniel Paleka , Nina Panickssery , Wes Gurnee , Neel Nanda

Optimization of offensive content moderation models for different types of hateful messages is typically achieved through continued pre-training or fine-tuning on new hate speech benchmarks. However, existing benchmarks mainly address…

Computation and Language · Computer Science 2026-04-07 Irina Proskurina , Marc-Antoine Carpentier , Julien Velcin

Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…

Artificial Intelligence · Computer Science 2025-10-30 Juan Ren , Mark Dras , Usman Naseem

While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting. We introduce the Robust Reasoning Benchmark (RRB), a pipeline of…

Machine Learning · Computer Science 2026-05-22 Pavel Golikov , Evgenii Opryshko , Gennady Pekhimenko , Mark C. Jeffrey

If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset. To test this, we take multilingual in-context learning as a case study, where few-shot…

Computation and Language · Computer Science 2026-04-02 Neeraja Kirtane , Kuan-Hao Huang

As pretrained models are increasingly shared on the web, ensuring that models can forget or delete sensitive, copyrighted, or private information upon request has become crucial. Machine unlearning has been proposed to address this…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Yurim Jang , Jaeung Lee , Dohyun Kim , Jaemin Jo , Simon S. Woo

We introduce a method to reduce refusal rates of large language models (LLMs) on sensitive content without modifying model weights or prompts. Motivated by the observation that refusals in certain models were often preceded by the specific…

Computation and Language · Computer Science 2025-06-02 Harvey Dam , Jonas Knochelmann , Vinu Joseph , Ganesh Gopalakrishnan

This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Anushka Sivakumar , Andrew Zhang , Zaber Hakim , Chris Thomas

Referring expression segmentation (RES), a task that involves localizing specific instance-level objects based on free-form linguistic descriptions, has emerged as a crucial frontier in human-AI interaction. It demands an intricate…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Ying Zang , Chenglong Fu , Runlong Cao , Didi Zhu , Min Zhang , Wenjun Hu , Lanyun Zhu , Tianrun Chen

Modern AI models contain much of human knowledge, yet understanding of their internal representation of this knowledge remains elusive. Characterizing the structure and properties of this representation will lead to improvements in model…

Computation and Language · Computer Science 2025-05-30 Daniel Beaglehole , Adityanarayanan Radhakrishnan , Enric Boix-Adserà , Mikhail Belkin

The recent explosion in the capabilities of large language models has led to a wave of interest in how best to prompt a model to perform a given task. While it may be tempting to simply choose a prompt based on average performance on a…

Machine Learning · Computer Science 2024-03-29 Thomas P. Zollo , Todd Morrill , Zhun Deng , Jake C. Snell , Toniann Pitassi , Richard Zemel

Visual grounding tasks, such as referring image segmentation (RIS) and referring expression comprehension (REC), aim to localize a target object based on a given textual description. The target object in an image can be described in…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Seonghoon Yu , Junbeom Hong , Joonseok Lee , Jeany Son

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…

Computation and Language · Computer Science 2025-10-16 Juan Ren , Mark Dras , Usman Naseem
‹ Prev 1 8 9 10 Next ›