English
Related papers

Related papers: Just Enough Shifts: Mitigating Over-Refusal in Ali…

200 papers

Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations. Existing methods do so by ablating a refusal direction from model activations, aiming…

Artificial Intelligence · Computer Science 2026-05-22 Giorgio Piras , Raffaele Mura , Fabio Brau , Maura Pintor , Luca Oneto , Fabio Roli , Battista Biggio

Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised finetuning on entire expert trajectories. However,…

Computation and Language · Computer Science 2025-06-06 Zhixun Chen , Ming Li , Yuxuan Huang , Yali Du , Meng Fang , Tianyi Zhou

User alignment is crucial for adapting general-purpose language models (LMs) to downstream tasks, but human annotations are often not available for all types of instructions, especially those with customized constraints. We observe that…

Computation and Language · Computer Science 2024-03-12 Fei Wang , Chao Shang , Sarthak Jain , Shuai Wang , Qiang Ning , Bonan Min , Vittorio Castelli , Yassine Benajiba , Dan Roth

Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) in alleviating hallucinations confronted with knowledge-intensive questions. RAG adopts information retrieval techniques to inject external…

Computation and Language · Computer Science 2024-10-10 Junda Zhu , Lingyong Yan , Haibo Shi , Dawei Yin , Lei Sha

Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (LMs). The self-improving mechanism often employs random…

Machine Learning · Computer Science 2025-10-07 Woosung Koh , Wonbeen Oh , Jaein Jang , MinHyung Lee , Hyeongjin Kim , Ah Yeon Kim , Joonkee Kim , Junghyun Lee , Taehyeon Kim , Se-Young Yun

Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures a complementary failure mode: denial of assistance to…

Cryptography and Security · Computer Science 2026-03-12 David Campbell , Neil Kale , Udari Madhushani Sehwag , Bert Herring , Nick Price , Dan Borges , Alex Levinson , Christina Q Knight

A broad use case of large language models (LLMs) is in goal-directed decision-making tasks (or "agent" tasks), where an LLM needs to not just generate completions for a given prompt, but rather make intelligent decisions over a multi-turn…

Machine Learning · Computer Science 2024-03-01 Yifei Zhou , Andrea Zanette , Jiayi Pan , Sergey Levine , Aviral Kumar

Large Language Models (LLMs) rely on safety alignment to obey safe requests while refusing harmful ones. However, traditional refusal mechanisms often lead to "rigid rejection," where a general template (e.g., "I cannot fulfill this…

Computation and Language · Computer Science 2026-05-11 Ying Zhang , Congyu Qiao , Xin Geng , Ning Xu

Refusal-Aware Instruction Tuning (RAIT) enables Large Language Models (LLMs) to refuse to answer unknown questions. By modifying responses of unknown questions in the training data to refusal responses such as "I don't know", RAIT enhances…

Computation and Language · Computer Science 2024-12-23 Runchuan Zhu , Zhipeng Ma , Jiang Wu , Junyuan Gao , Jiaqi Wang , Dahua Lin , Conghui He

Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving…

Computation and Language · Computer Science 2026-03-30 Hongxiang Zhang , Yuan Tian , Tianyi Zhang

Access control is a cornerstone of secure computing, yet large language models often blur role boundaries by producing unrestricted responses. We study role-conditioned refusals, focusing on the LLM's ability to adhere to access control…

Computation and Language · Computer Science 2025-10-10 Đorđe Klisura , Joseph Khoury , Ashish Kundu , Ram Krishnan , Anthony Rios

Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support…

Computation and Language · Computer Science 2023-10-24 Bingsheng Yao , Ishan Jindal , Lucian Popa , Yannis Katsis , Sayan Ghosh , Lihong He , Yuxuan Lu , Shashank Srivastava , Yunyao Li , James Hendler , Dakuo Wang

With the wide application of large language models (LLMs), the problems of bias and value inconsistency in sensitive domains have gradually emerged, especially in terms of race, society and politics. In this paper, we propose an adversarial…

Computation and Language · Computer Science 2026-01-23 Yuan Gao , Zhigang Liu , Xinyu Yao , Bo Chen , Xiaobing Zhao

We present two categories of model-agnostic adversarial strategies that reveal the weaknesses of several generative, task-oriented dialogue models: Should-Not-Change strategies that evaluate over-sensitivity to small and…

Computation and Language · Computer Science 2018-09-07 Tong Niu , Mohit Bansal

We propose affine concept editing (ACE) as an approach for steering language models' behavior by intervening directly in activations. We begin with an affine decomposition of model activation vectors and show that prior methods for steering…

Machine Learning · Computer Science 2025-01-29 Thomas Marshall , Adam Scherlis , Nora Belrose

We introduce LLM SELECTOR, the first framework for active model selection of Large Language Models (LLMs). Unlike prior evaluation and benchmarking approaches that rely on fully annotated datasets, LLM SELECTOR efficiently identifies the…

Computation and Language · Computer Science 2025-10-13 Yavuz Durmazkeser , Patrik Okanovic , Andreas Kirsch , Torsten Hoefler , Nezihe Merve Gürel

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Cryptography and Security · Computer Science 2025-05-30 Jinchuan Zhang , Lu Yin , Yan Zhou , Songlin Hu

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

Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations,…

Computation and Language · Computer Science 2026-05-18 Jiahui Guang , Yingjie Zhu , Cuiyun Gao , Haiyan Wang , Jing Li , Di Shao , Zhaoquan Gu

This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algorithms achieve high prediction performance, they are…

Machine Learning · Computer Science 2020-10-27 Masahiro Kato , Zhenghang Cui , Yoshihiro Fukuhara
‹ Prev 1 4 5 6 7 8 10 Next ›