English
Related papers

Related papers: SOM Directions are Better than One: Multi-Directio…

200 papers

Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we lack a robust understanding of why LLMs are susceptible to jailbreaks, future frontier models operating more…

Artificial Intelligence · Computer Science 2026-05-04 Shubham Kumar , Narendra Ahuja

We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive topics without retraining. We replace fragile pattern-based refusal detection…

Computation and Language · Computer Science 2026-02-25 Iker García-Ferrero , David Montero , Roman Orus

Large Language Models (LLMs) are widely used across sectors, yet their alignment with International Humanitarian Law (IHL) is not well understood. This study evaluates eight leading LLMs on their ability to refuse prompts that explicitly…

Computers and Society · Computer Science 2025-06-10 John Mavi , Diana Teodora Găitan , Sergio Coronado

In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly…

Artificial Intelligence · Computer Science 2026-05-28 Matteo Gioele Collu , Riccardo Conte , Alberto Giaretta , Denis Kleyko , Mauro Conti , Matteo Zavatteri , Roberto Confalonieri

A key component of building safe and reliable language models is enabling the models to appropriately refuse to follow certain instructions or answer certain questions. We may want models to output refusal messages for various categories of…

Machine Learning · Computer Science 2025-09-01 Neel Jain , Aditya Shrivastava , Chenyang Zhu , Daben Liu , Alfy Samuel , Ashwinee Panda , Anoop Kumar , Micah Goldblum , Tom Goldstein

Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark…

Computation and Language · Computer Science 2025-12-19 Shuzhou Yuan , Ercong Nie , Yinuo Sun , Chenxuan Zhao , William LaCroix , Michael Färber

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Computation and Language · Computer Science 2025-07-16 Zhehao Zhang , Weijie Xu , Fanyou Wu , Chandan K. Reddy

Omni-modal Large Language Models (OLLMs) greatly expand LLMs' multimodal capabilities but also introduce cross-modal safety risks. However, a systematic understanding of vulnerabilities in omni-modal interactions remains lacking. To bridge…

Cryptography and Security · Computer Science 2026-02-12 Kun Wang , Zherui Li , Zhenhong Zhou , Yitong Zhang , Yan Mi , Kun Yang , Yiming Zhang , Junhao Dong , Zhongxiang Sun , Qiankun Li , Yang Liu

Refusal behavior in aligned LLMs is often viewed as model-specific, yet we hypothesize it stems from a universal, low-dimensional semantic circuit shared across models. To test this, we introduce Trajectory Replay via Concept-Basis…

Computation and Language · Computer Science 2026-01-27 Tony Cristofano

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they often refuse to answer legitimate queries--a phenomenon known as overrefusal. Overrefusal typically stems from over-conservative…

Artificial Intelligence · Computer Science 2025-09-18 Licheng Pan , Yongqi Tong , Xin Zhang , Xiaolu Zhang , Jun Zhou , Zhixuan Chu

Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates: routing from concept detection to behavioral policy. We…

Machine Learning · Computer Science 2026-05-04 Gregory N. Frank

Self-Organizing Map (SOM) is a neural network model which is used to obtain a topology-preserving mapping from the (usually high dimensional) input/feature space to an output/map space of fewer dimensions (usually two or three in order to…

Artificial Intelligence · Computer Science 2016-05-20 Gerasimos Spanakis , Gerhard Weiss

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Computation and Language · Computer Science 2025-10-01 Yuyou Zhang , Miao Li , William Han , Yihang Yao , Zhepeng Cen , Ding Zhao

With the rapid advancement of Vision Language Models (VLMs), refusal mechanisms have become a critical component for ensuring responsible and safe model behavior. However, existing refusal strategies are largely \textit{one-size-fits-all}…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Jiaxi Yang , Shicheng Liu , Yuchen Yang , Dongwon Lee

Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal,…

Computation and Language · Computer Science 2025-06-17 Justin Cui , Wei-Lin Chiang , Ion Stoica , Cho-Jui Hsieh

Backpropagation-based supervised learning has achieved great success in computer vision tasks. However, its biological plausibility is always controversial. Recently, the bio-inspired Hebbian learning rule (HLR) has received extensive…

Computer Vision and Pattern Recognition · Computer Science 2023-03-17 Jiahong Zhang , Lihong Cao , Moning Zhang , Wenlong Fu

Large language models (LLMs) are increasingly integrated into our daily lives and personalized. However, LLM personalization might also increase unintended side effects. Recent work suggests that persona prompting can lead models to falsely…

Computation and Language · Computer Science 2025-09-11 Flor Miriam Plaza-del-Arco , Paul Röttger , Nino Scherrer , Emanuele Borgonovo , Elmar Plischke , Dirk Hovy

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

Large language models (LLMs) have demonstrated impressive language understanding and generation capabilities, enabling them to answer a wide range of questions across various domains. However, these models are not flawless and often produce…

Computation and Language · Computer Science 2024-09-23 Lang Cao

Despite the outstanding performance of Large language Models (LLMs) in diverse tasks, they are vulnerable to jailbreak attacks, wherein adversarial prompts are crafted to bypass their security mechanisms and elicit unexpected responses.…

Cryptography and Security · Computer Science 2025-04-25 Zeqing He , Zhibo Wang , Zhixuan Chu , Huiyu Xu , Wenhui Zhang , Qinglong Wang , Rui Zheng