English
Related papers

Related papers: A Paired Testing Protocol for Batch-Conditioned Re…

200 papers

Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as…

Multicalibration requires predicted scores to agree with label probabilities across rich families of subgroups and score-dependent tests, but existing methods require clean input-label pairs for evaluation and post-processing. This…

Machine Learning · Statistics 2026-05-12 Futoshi Futami , Takashi Ishida

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Cryptography and Security · Computer Science 2025-09-09 Youjia Zheng , Mohammad Zandsalimy , Shanu Sushmita

Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive…

Cryptography and Security · Computer Science 2026-03-19 Taiwo Onitiju , Iman Vakilinia

Evaluating the in-context learning classification performance of language models poses challenges due to small dataset sizes, extensive prompt-selection using the validation set, and intentionally difficult tasks that lead to near-random…

Computation and Language · Computer Science 2024-11-12 Gregory Yauney , David Mimno

Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models may refuse requests that are unsafe for general users but…

Artificial Intelligence · Computer Science 2026-05-26 Qitao Tan , Xiaoying Song , Arman Akbari , Arash Akbari , Yanzhi Wang , Xiaoming Zhai , Lingzi Hong , Zhen Xiang , Jin Lu , Geng Yuan

Ensuring Vision-Language Models (VLMs) generate safe outputs is crucial for their reliable deployment. However, LVLMs suffer from drastic safety degradation compared to their LLM backbone. Even blank or irrelevant images can trigger LVLMs…

Artificial Intelligence · Computer Science 2025-06-02 Wenhan Yang , Spencer Stice , Ali Payani , Baharan Mirzasoleiman

The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem…

Cryptography and Security · Computer Science 2026-03-26 Oleksandr Yarotskyi , José D'Abruzzo Pereira , João R. Campos

As large language models (LLMs) transition from chat interfaces to integral components of stochastic pipelines and systems approaching general intelligence, the ability to faithfully sample from specified probability distributions has…

Computation and Language · Computer Science 2026-04-27 Minda Zhao , Yilun Du , Mengyu Wang

LLM confidence signals are used for abstention, routing, and safety-critical decisions. No standard practice exists for checking whether a confidence signal carries item-level information before building on it. We transfer the validity…

Computation and Language · Computer Science 2026-04-21 Jon-Paul Cacioli

Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emergence of their properties and encoded knowledge, the risk of…

Computation and Language · Computer Science 2023-08-31 Rishabh Bhardwaj , Soujanya Poria

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

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…

Computation and Language · Computer Science 2026-05-05 Jialin Song , Xiaodong Liu , Weiwei Yang , Wuyang Chen , Mingqian Feng , Xuekai Zhu , Jianfeng Gao

Safety alignment mechanisms in large language models prevent responses to harmful queries through learned refusal behavior, yet these same mechanisms impede legitimate research applications including cognitive modeling, adversarial testing,…

Computation and Language · Computer Science 2026-01-09 Richard J. Young

The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to…

Cryptography and Security · Computer Science 2026-01-13 Xin Wang , Yunhao Chen , Juncheng Li , Yixu Wang , Yang Yao , Tianle Gu , Jie Li , Yan Teng , Yingchun Wang , Xia Hu

Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional components. However, existing safety attribution methods…

Machine Learning · Computer Science 2026-03-25 Miao Yu , Siyuan Fu , Moayad Aloqaily , Zhenhong Zhou , Safa Otoum , Xing fan , Kun Wang , Yufei Guo , Qingsong Wen

Understanding how large language models (LLMs) process emotionally sensitive content is critical for building safe and reliable systems, particularly in mental health contexts. We investigate the scaling behavior of LLMs on two key tasks:…

Computation and Language · Computer Science 2025-09-08 Edoardo Pinzuti , Oliver Tüscher , André Ferreira Castro

Large Language Models (LLMs) are increasingly relied upon for complex workflows, yet their ability to maintain flow of instructions remains underexplored. Existing benchmarks conflate task complexity with structural ordering, making it…

Artificial Intelligence · Computer Science 2026-01-28 Andrew Jaffe , Noah Reicin , Jinho D. Choi

Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking. We thus develop SecLLMHolmes, a fully automated evaluation…

Cryptography and Security · Computer Science 2024-07-25 Saad Ullah , Mingji Han , Saurabh Pujar , Hammond Pearce , Ayse Coskun , Gianluca Stringhini

Large Language Models (LLMs) are increasingly used for medical entity extraction, yet their confidence scores are often miscalibrated, limiting safe deployment in clinical settings. We present a conformal prediction framework that provides…

Computation and Language · Computer Science 2026-03-10 Manil Shrestha , Edward Kim
‹ Prev 1 4 5 6 7 8 10 Next ›