English
Related papers

Related papers: Useless but Safe? Benchmarking Utility Recovery wi…

200 papers

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Computation and Language · Computer Science 2025-06-24 Laurène Vaugrante , Francesca Carlon , Maluna Menke , Thilo Hagendorff

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

Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however, often miss these topic shifts and carry over irrelevant context from previous turns,…

Computation and Language · Computer Science 2026-05-12 Aditya Sinha , Harald Steck , Vito Ostuni , Matteo Rinaldi

Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature…

Cryptography and Security · Computer Science 2026-05-01 Prashant Kulkarni

Rapid deployment of vision-language models (VLMs) magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate…

Computation and Language · Computer Science 2025-09-24 DongGeon Lee , Joonwon Jang , Jihae Jeong , Hwanjo Yu

Multi-Turn Long-Form Question Answering (MT-LFQA) is a key application paradigm of Large Language Models (LLMs) in knowledge-intensive domains. However, existing benchmarks are limited to single-turn dialogue, while multi-turn dialogue…

Computation and Language · Computer Science 2025-09-29 Junhao Chen , Yu Huang , Siyuan Li , Rui Yao , Hanqian Li , Hanyu Zhang , Jungang Li , Jian Chen , Bowen Wang , Xuming Hu

Large language models (LLMs) have been widely used for mental health support. However, current safety evaluations in this field are mostly limited to detecting whether LLMs output prohibited words in single-turn conversations, neglecting…

Computation and Language · Computer Science 2026-01-22 Youyou Cheng , Zhuangwei Kang , Kerry Jiang , Chenyu Sun , Qiyang Pan

The growing use of large language model (LLM)-based chatbots has raised concerns about fairness. Fairness issues in LLMs can lead to severe consequences, such as bias amplification, discrimination, and harm to marginalized communities.…

Computation and Language · Computer Science 2025-06-11 Zhiting Fan , Ruizhe Chen , Tianxiang Hu , Zuozhu Liu

Large language models (LLMs) have demonstrated revolutionary capabilities in understanding complex contexts and performing a wide range of tasks. However, LLMs can also answer questions that are unethical or harmful, raising concerns about…

Cryptography and Security · Computer Science 2025-04-15 Kang Yang , Guanhong Tao , Xun Chen , Jun Xu

Language models (LMs) are increasingly used in collaboration: multiple LMs trained by different parties collaborate through routing systems, multi-agent debate, model merging, and more. Critical safety risks remain in this decentralized…

Computation and Language · Computer Science 2026-02-06 Ziyuan Yang , Wenxuan Ding , Shangbin Feng , Yulia Tsvetkov

Unlimited, or so-called helpful-only language models are trained without safety alignment constraints and never refuse user queries. They are widely used by leading AI companies as internal tools for red teaming and alignment evaluation.…

Computation and Language · Computer Science 2025-08-26 Jiahao Zhao , Liwei Dong

We investigate a failure mode of large language models (LLMs) in which plain-text prompts elicit excessive outputs, a phenomenon we term Overflow. Unlike jailbreaks or prompt injection, Overflow arises under ordinary interaction settings…

Computation and Language · Computer Science 2026-01-14 Erin Feiglin , Nir Hutnik , Raz Lapid

Large language models (LLMs) have demonstrated remarkable performance on single-turn text-to-SQL tasks, but real-world database applications predominantly require multi-turn interactions to handle ambiguous queries, execution errors, and…

The widespread adoption of Large Language Models (LLMs) raises concerns about the potential harmfulness of their responses. In this paper, we first investigate the harmfulness of responses from four general-purpose LLMs. Next, we propose…

Software Engineering · Computer Science 2026-05-11 Giordano d'Aloisio , David Williams , Giusy Annunziata , Zhiwei Fei , Antinisca Di Marco , Federica Sarro

Despite extensive safety alignment efforts, large language models (LLMs) remain vulnerable to jailbreak attacks that elicit harmful behavior. While existing studies predominantly focus on attack methods that require technical expertise, two…

Machine Learning · Computer Science 2025-08-05 Yik Siu Chan , Narutatsu Ri , Yuxin Xiao , Marzyeh Ghassemi

Integration of Large Language Models with search/retrieval engines has become ubiquitous, yet these systems harbor a critical vulnerability that undermines their reliability. We present the first systematic investigation of "chameleon…

Computation and Language · Computer Science 2025-10-28 Shivam Ratnakar , Sanjay Raghavendra

Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not only incur significant computational overhead during…

Machine Learning · Computer Science 2026-01-07 Jiawen Zhang , Lipeng He , Kejia Chen , Jian Lou , Jian Liu , Xiaohu Yang , Ruoxi Jia

Multimodal Large Language Models (MLLMs) are showing strong safety concerns (e.g., generating harmful outputs for users), which motivates the development of safety evaluation benchmarks. However, we observe that existing safety benchmarks…

Cryptography and Security · Computer Science 2024-10-25 Zonghao Ying , Aishan Liu , Siyuan Liang , Lei Huang , Jinyang Guo , Wenbo Zhou , Xianglong Liu , Dacheng Tao

Large language models are being deployed as mental health support agents at scale, yet only 16% of LLM-based chatbot interventions have undergone rigorous clinical efficacy testing, and simulations reveal psychological deterioration in over…

Computation and Language · Computer Science 2026-04-28 Suhas BN , Andrew M. Sherrill , Rosa I. Arriaga , Chris W. Wiese , Saeed Abdullah

With the increasing use of large language models (LLMs) in medical decision-support, it is essential to evaluate not only their final answers but also the reliability of their reasoning. Two key risks are Chain-of-Thought (CoT) faithfulness…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Kaiyuan Ji , Yijin Guo , Zicheng Zhang , Xiangyang Zhu , Yuan Tian , Ning Liu , Guangtao Zhai
‹ Prev 1 4 5 6 7 8 10 Next ›