English
Related papers

Related papers: When Safety Blocks Sense: Measuring Semantic Confu…

200 papers

Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety…

Artificial Intelligence · Computer Science 2025-10-08 Qingyu Yin , Chak Tou Leong , Linyi Yang , Wenxuan Huang , Wenjie Li , Xiting Wang , Jaehong Yoon , YunXing , XingYu , Jinjin Gu

Frontier large language models are increasingly deployed as orchestration backbones for biological research workflows, yet no shared evidence base exists for comparing their refusal behaviour on legitimate research prompts. RefusalBench,…

Software Engineering · Computer Science 2026-05-22 Lukas Weidener , Marko Brkić , Mihailo Jovanović , Emre Ulgac , Aakaash Meduri

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify…

Computation and Language · Computer Science 2025-05-30 Wei Jie Yeo , Nirmalendu Prakash , Clement Neo , Roy Ka-Wei Lee , Erik Cambria , Ranjan Satapathy

As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this…

Artificial Intelligence · Computer Science 2026-03-24 Gregory M. Ruddell

Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in \emph{over-refusal} of benign queries or \emph{unsafe compliance} with harmful ones. While existing…

Artificial Intelligence · Computer Science 2026-01-27 Zhihao Zhang , Liting Huang , Guanghao Wu , Preslav Nakov , Heng Ji , Usman Naseem

In the realm of Large Language Model (LLM) functionalities, providing reliable information is paramount, yet reports suggest that LLM outputs lack consistency. This inconsistency, often at-tributed to randomness in token sampling,…

Computation and Language · Computer Science 2024-10-22 Yanggyu Lee , Jihie Kim

Detecting when a language model is wrong without ground truth labels is a fundamental challenge for safe deployment. Existing approaches rely on a model's own uncertainty -- such as token entropy or confidence scores -- but these signals…

Artificial Intelligence · Computer Science 2026-03-27 Matt Gorbett , Suman Jana

There is an increasing interest in using language models (LMs) for automated decision-making, with multiple countries actively testing LMs to aid in military crisis decision-making. To scrutinize relying on LM decision-making in high-stakes…

Computation and Language · Computer Science 2024-10-22 Aryan Shrivastava , Jessica Hullman , Max Lamparth

Misalignment in Large Language Models (LLMs) arises when model behavior diverges from human expectations and fails to simultaneously satisfy safety, value, and cultural dimensions, which must co-occur in real-world settings to solve a…

Computation and Language · Computer Science 2026-02-13 Usman Naseem , Gautam Siddharth Kashyap , Rafiq Ali , Ebad Shabbir , Sushant Kumar Ray , Abdullah Mohammad , Agrima Seth

Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion models, MLLMs possess a much stronger capability for semantic understanding, enabling them to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Ye Leng , Junjie Chu , Mingjie Li , Chenhao Lin , Chao Shen , Michael Backes , Yun Shen , Yang Zhang

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…

Computation and Language · Computer Science 2024-04-02 Yixu Wang , Yan Teng , Kexin Huang , Chengqi Lyu , Songyang Zhang , Wenwei Zhang , Xingjun Ma , Yu-Gang Jiang , Yu Qiao , Yingchun Wang

Consistency, which refers to the capability of generating the same predictions for semantically similar contexts, is a highly desirable property for a sound language understanding model. Although recent pretrained language models (PLMs)…

Computation and Language · Computer Science 2021-08-17 Myeongjun Jang , Deuk Sin Kwon , Thomas Lukasiewicz

Large language models (LLMs) can exhibit concept-conditioned semantic divergence: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like responses that evade token-trigger audits. This behavior falls…

Computation and Language · Computer Science 2026-01-28 Nay Myat Min , Long H. Pham , Yige Li , Jun Sun

Large language model safety evaluation remains heavily English-centered, leaving low-resource languages under-measured even when models are deployed globally. We evaluate four open-weight instruction-tuned models on SomaliBench v0, a…

Computation and Language · Computer Science 2026-05-26 Khalid Yusuf Dahir

Despite the impressive capabilities of Large Language Models (LLMs) in various tasks, their vulnerability to unsafe prompts remains a critical issue. These prompts can lead LLMs to generate responses on illegal or sensitive topics, posing a…

Computation and Language · Computer Science 2024-07-10 Jinseok Kim , Jaewon Jung , Sangyeop Kim , Sohyung Park , Sungzoon Cho

Large Language Models (LLMs) can generate text by transferring style attributes like formality resulting in formal or informal text. However, instructing LLMs to generate text that when spoken, is more intelligible in an acoustically…

Computation and Language · Computer Science 2024-08-09 Anupama Chingacham , Miaoran Zhang , Vera Demberg , Dietrich Klakow

From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response signifies safe reasoning throughout the entire process.…

Computation and Language · Computer Science 2026-02-17 Zhao Tong , Chunlin Gong , Yiping Zhang , Haichao Shi , Qiang Liu , Xingcheng Xu , Shu Wu , Xiao-Yu Zhang

Safety evaluations of language models often treat serving configuration as fixed background infrastructure, but batch condition is an untested treatment variable whenever the same prompt may be evaluated alone, in a synchronized batch, or…

Machine Learning · Computer Science 2026-05-28 Sahil Kadadekar

Large Language Models (LLMs), despite their impressive capabilities, often fail to accurately repeat a single word when prompted to, and instead output unrelated text. This unexplained failure mode represents a vulnerability, allowing even…

Machine Learning · Computer Science 2025-03-13 Itay Yona , Ilia Shumailov , Jamie Hayes , Federico Barbero , Yossi Gandelsman

Researchers are increasingly using language models (LMs) for text annotation. These approaches rely only on a prompt telling the model to return a given output according to a set of instructions. The reproducibility of LM outputs may…

Computation and Language · Computer Science 2026-05-18 Christopher Barrie , Elli Palaiologou , Petter Törnberg
‹ Prev 1 3 4 5 6 7 10 Next ›