English
Related papers

Related papers: Unintended Misalignment from Agentic Fine-Tuning: …

200 papers

Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools. We…

Artificial Intelligence · Computer Science 2025-05-20 Maxime Robeyns , Martin Szummer , Laurence Aitchison

Agentic search requires large language models (LLMs) to perform multi-step search to solve complex information-seeking tasks, imposing unique challenges on their reasoning capabilities. However, what constitutes effective reasoning for…

Artificial Intelligence · Computer Science 2026-01-19 Jiahe Jin , Abhijay Paladugu , Chenyan Xiong

Multi-agent LLM systems introduce a security risk in which sensitive information accessed by one agent can propagate through shared context and reappear in downstream outputs, even without explicit adversarial intent. We formalise this…

Artificial Intelligence · Computer Science 2026-05-12 Riya Tapwal , Abhishek Kumar , Carsten Maple

LLM agents are widely used as agents for customer support, content generation, and code assistance. However, they are vulnerable to prompt injection attacks, where adversarial inputs manipulate the model's behavior. Traditional defenses…

Cryptography and Security · Computer Science 2025-06-09 Zhilong Wang , Neha Nagaraja , Lan Zhang , Hayretdin Bahsi , Pawan Patil , Peng Liu

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

Machine Learning · Computer Science 2025-09-29 Sathwik Karnik , Somil Bansal

Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes. As tense jailbreaking demonstrates that models refusing harmful requests often comply when…

Artificial Intelligence · Computer Science 2026-04-15 Yein Park , Jungwoo Park , Jaewoo Kang

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Computation and Language · Computer Science 2025-04-07 Jaymari Chua , Chen Wang , Lina Yao

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Cryptography and Security · Computer Science 2025-06-09 Yuan Xun , Siyuan Liang , Xiaojun Jia , Xinwei Liu , Xiaochun Cao

Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks. As MAS become increasingly autonomous in various safety-critical tasks, detecting malicious agents has become a critical…

Cryptography and Security · Computer Science 2025-12-23 Junjun Pan , Yixin Liu , Rui Miao , Kaize Ding , Yu Zheng , Quoc Viet Hung Nguyen , Alan Wee-Chung Liew , Shirui Pan

The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…

Machine Learning · Computer Science 2021-11-11 Paulina Stevia Nouwou Mindom , Amin Nikanjam , Foutse Khomh , John Mullins

Large language models (LLMs) remain unreliable for global enterprise applications due to substantial performance gaps between high-resource and mid/low-resource languages, driven by English-centric pretraining and internal reasoning biases.…

Computation and Language · Computer Science 2025-10-28 Amit Agarwal , Hansa Meghwani , Hitesh Laxmichand Patel , Tao Sheng , Sujith Ravi , Dan Roth

In this paper, we tackle the emerging challenge of unintended harmful content generation in Large Language Models (LLMs) with a novel dual-stage optimisation technique using adversarial fine-tuning. Our two-pronged approach employs an…

Computation and Language · Computer Science 2023-08-29 Charles O'Neill , Jack Miller , Ioana Ciuca , Yuan-Sen Ting , Thang Bui

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by…

Machine Learning · Computer Science 2026-05-27 Kevin Kuo , Chhavi Yadav , Virginia Smith

Advances in Large Language Models (LLMs) have enabled a new class of self-evolving agents that autonomously improve through interaction with the environment, demonstrating strong capabilities. However, self-evolution also introduces novel…

Artificial Intelligence · Computer Science 2026-03-10 Shuai Shao , Qihan Ren , Chen Qian , Boyi Wei , Dadi Guo , Jingyi Yang , Xinhao Song , Linfeng Zhang , Weinan Zhang , Dongrui Liu , Jing Shao

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Cryptography and Security · Computer Science 2026-05-05 Lingxi Zhang , Guangtao Zheng , Hanjie Chen

Finetuning open-weight Large Language Models (LLMs) is standard practice for achieving task-specific performance improvements. Until now, finetuning has been regarded as a controlled and secure process in which training on benign datasets…

Machine Learning · Computer Science 2025-10-10 Thibaud Gloaguen , Mark Vero , Robin Staab , Martin Vechev

Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web,…

Artificial Intelligence · Computer Science 2026-04-07 Anshuman Chhabra , Shrestha Datta , Shahriar Kabir Nahin , Prasant Mohapatra

Large Language Models (LLMs), especially their compact efficiency-oriented variants, remain susceptible to jailbreak attacks that can elicit harmful outputs despite extensive alignment efforts. Existing adversarial prompt generation…

Fine-tuning-as-a-Service introduces a critical vulnerability where a few malicious examples mixed into the user's fine-tuning dataset can compromise the safety alignment of Large Language Models (LLMs). While a recognized paradigm frames…

Computation and Language · Computer Science 2025-08-12 Biao Yi , Jiahao Li , Baolei Zhang , Lihai Nie , Tong Li , Tiansheng Huang , Zheli Liu

Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose…

‹ Prev 1 8 9 10 Next ›