English
Related papers

Related papers: SABER: Small Actions, Big Errors -- Safeguarding M…

200 papers

Large Language Models (LLMs) have shown tremendous potential as agents, excelling at tasks that require multiple rounds of reasoning and interactions. Rejection Sampling Fine-Tuning (RFT) has emerged as an effective method for finetuning…

Artificial Intelligence · Computer Science 2025-04-22 Li-Cheng Lan , Andrew Bai , Minhao Cheng , Cho-Jui Hsieh , Tianyi Zhou

Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. However, existing multi-turn RL algorithms for optimizing LLM agents fail to perform effective credit assignment over multiple turns while…

Machine Learning · Computer Science 2025-03-20 Yifei Zhou , Song Jiang , Yuandong Tian , Jason Weston , Sergey Levine , Sainbayar Sukhbaatar , Xian Li

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse…

Cryptography and Security · Computer Science 2024-06-26 Yi Zeng , Weiyu Sun , Tran Ngoc Huynh , Dawn Song , Bo Li , Ruoxi Jia

Large Language Models (LLMs) show promise as data analysis agents, but existing benchmarks overlook the iterative nature of the field, where experts' decisions evolve with deeper insights of the dataset. To address this, we introduce…

Computation and Language · Computer Science 2025-06-09 Hanyu Li , Haoyu Liu , Tingyu Zhu , Tianyu Guo , Zeyu Zheng , Xiaotie Deng , Michael I. Jordan

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…

Machine Learning · Computer Science 2026-02-10 Kaustubh Ponkshe , Shaan Shah , Raghav Singhal , Praneeth Vepakomma

Large Language Models (LLMs) as clinical agents require careful behavioral adaptation. While adept at reactive tasks (e.g., diagnosis reasoning), LLMs often struggle with proactive engagement, like unprompted identification of critical…

The deployment of Large Language Models (LLMs) as autonomous economic agents introduces systemic risks that extend beyond individual capability failures. As agents transition to directly interacting with marketplaces, their collective…

Machine Learning · Computer Science 2026-05-19 Seth Karten , Cameron Crow , Chi Jin

The existing safety alignment of Large Language Models (LLMs) is found fragile and could be easily attacked through different strategies, such as through fine-tuning on a few harmful examples or manipulating the prefix of the generation…

Computation and Language · Computer Science 2024-05-28 Chak Tou Leong , Yi Cheng , Kaishuai Xu , Jian Wang , Hanlin Wang , Wenjie Li

Proactive interventions by LLM critic models are often assumed to improve reliability, yet their effects at deployment time are poorly understood. We show that a binary LLM critic with strong offline accuracy (AUROC 0.94) can nevertheless…

Computation and Language · Computer Science 2026-02-04 Rakshith Vasudev , Melisa Russak , Dan Bikel , Waseem Alshikh

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…

Computation and Language · Computer Science 2025-07-18 Zijian Zhou , Ao Qu , Zhaoxuan Wu , Sunghwan Kim , Alok Prakash , Daniela Rus , Jinhua Zhao , Bryan Kian Hsiang Low , Paul Pu Liang

Large language models (LLMs) are increasingly deployed as autonomous agents in offensive cybersecurity. In this paper, we reveal an interesting phenomenon: different agents exhibit distinct attack patterns. Specifically, each agent exhibits…

Cryptography and Security · Computer Science 2026-05-11 Taein Lim , Seongyong Ju , Munhyeok Kim , Hyunjun Kim , Hoki Kim

Finetuning on narrow domains has become an essential tool to adapt Large Language Models (LLMs) to specific tasks and to create models with known unusual properties that are useful for research. We show that narrow finetuning creates strong…

Computation and Language · Computer Science 2026-03-06 Julian Minder , Clément Dumas , Stewart Slocum , Helena Casademunt , Cameron Holmes , Robert West , Neel Nanda

Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving. However, malicious agents in MAS may inject misinformation…

Artificial Intelligence · Computer Science 2026-05-28 Yaoyang Luo , Zhi Zheng , Ziwei Zhao , Tong Xu , Zhao Jielun , Wenjun Xue , Yong Chen , Enhong Chen

Large language model (LLM)-based multi-agent systems are challenging to debug because failures often arise from long, branching interaction traces. The prevailing practice is to leverage LLMs for log-based failure localization, attributing…

Artificial Intelligence · Computer Science 2026-02-03 Ming Ma , Jue Zhang , Fangkai Yang , Yu Kang , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang

Standard benchmarks fixate on how well large language model (LLM) agents perform in finance, yet say little about whether they are safe to deploy. We argue that accuracy metrics and return-based scores provide an illusion of reliability,…

General Finance · Quantitative Finance 2025-06-03 Zichen Chen , Jiaao Chen , Jianda Chen , Misha Sra

Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination (test set exposure during training) risk masking true generalization. This concern extends to…

Artificial Intelligence · Computer Science 2025-06-10 Ming Liu , Wensheng Zhang

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Artificial Intelligence · Computer Science 2025-10-01 Qinjian Zhao , Jiaqi Wang , Zhiqiang Gao , Zhihao Dou , Belal Abuhaija , Kaizhu Huang

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it,…

Artificial Intelligence · Computer Science 2026-05-28 Dasol Choi , Alex Kwon

Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To better understand the limitations of such monitors against…

Cryptography and Security · Computer Science 2026-05-20 Elle Najt , Colin Toft , Tyler Tracy , Fabien Roger , Joe Benton

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Cryptography and Security · Computer Science 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He
‹ Prev 1 4 5 6 7 8 10 Next ›