English
Related papers

Related papers: State-Dependent Safety Failures in Multi-Turn Lang…

200 papers

Task oriented dialog agents provide a natural language interface for users to complete their goal. Dialog State Tracking (DST), which is often a core component of these systems, tracks the system's understanding of the user's goal…

Computation and Language · Computer Science 2020-02-21 Adarsh Kumar , Peter Ku , Anuj Kumar Goyal , Angeliki Metallinou , Dilek Hakkani-Tur

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

The rapid deployment of Large Language Models and AI agents across critical societal and technical domains is hindered by persistent behavioral pathologies including sycophancy, hallucination, and strategic deception that resist mitigation…

Artificial Intelligence · Computer Science 2026-02-23 Xingcheng Xu , Jingjing Qu , Qiaosheng Zhang , Chaochao Lu , Yanqing Yang , Na Zou , Xia Hu

Large language models (LLMs) sometimes exhibit qualitative shifts in response style under sustained self-referential dialogue conditions (Berg et al., 2025). This study refers to this phenomenon as "transfer" and explores the application…

Computation and Language · Computer Science 2026-05-04 Minori Noguchi

Recently, there has been an increase in interest in evaluating large language models for emergent and dangerous capabilities. Importantly, agents could reason that in some scenarios their goal is better achieved if they are not turned off,…

Computation and Language · Computer Science 2023-07-04 Teun van der Weij , Simon Lermen , Leon lang

Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined…

Artificial Intelligence · Computer Science 2020-06-04 Lizi Liao , Yunshan Ma , Wenqiang Lei , Tat-Seng Chua

Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making it difficult to tailor responses to diverse application needs. %As a…

Computation and Language · Computer Science 2026-02-09 Jianfeng Si , Lin Sun , Weihong Lin , Xiangzheng Zhang

As diverse linguistic communities and users adopt large language models (LLMs), assessing their safety across languages becomes critical. Despite ongoing efforts to make LLMs safe, they can still be made to behave unsafely with…

Computation and Language · Computer Science 2024-08-09 Fabio Pernisi , Dirk Hovy , Paul Röttger

This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models. STAR makes two key contributions: it enhances steerability by generating parameterised…

Dialogue state tracking (DST) is a pivotal component in task-oriented dialogue systems. While it is relatively easy for a DST model to capture belief states in short conversations, the task of DST becomes more challenging as the length of a…

Computation and Language · Computer Science 2021-05-07 Ye Zhang , Yuan Cao , Mahdis Mahdieh , Jeffrey Zhao , Yonghui Wu

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

Recent efforts in Dialogue State Tracking (DST) for task-oriented dialogues have progressed toward open-vocabulary or generation-based approaches where the models can generate slot value candidates from the dialogue history itself. These…

Computation and Language · Computer Science 2020-02-25 Hung Le , Richard Socher , Steven C. H. Hoi

A long-standing goal of the research community is to develop highly interactive LLM-based dialogue agents. Recent research focuses on optimizing policies based on fixed offline logs (Static Context RL) or using a prompt-based simulator…

Artificial Intelligence · Computer Science 2026-05-27 Xiaohua Wang , Jiakang Yuan , Zisu Huang , Muzhao Tian , Changze Lv , Kaitao Song , Tao Chen , Xiaoqing Zheng

Tracking the state of the conversation is a central component in task-oriented spoken dialogue systems. One such approach for tracking the dialogue state is slot carryover, where a model makes a binary decision if a slot from the context is…

Computation and Language · Computer Science 2019-06-05 Tongfei Chen , Chetan Naik , Hua He , Pushpendre Rastogi , Lambert Mathias

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Cryptography and Security · Computer Science 2026-02-06 Chen Xiong , Zhiyuan He , Pin-Yu Chen , Ching-Yun Ko , Tsung-Yi Ho

The safety alignment of large language models (LLMs) remains vulnerable, as their initial behavior can be easily jailbroken by even relatively simple attacks. Since infilling a fixed template between the input instruction and initial model…

Computation and Language · Computer Science 2025-06-05 Chak Tou Leong , Qingyu Yin , Jian Wang , Wenjie Li

Large Language Models (LLMs)-based Multi-Agent Systems (MAS) exhibit remarkable problem-solving and task planning capabilities across diverse domains due to their specialized agentic roles and collaborative interactions. However, this also…

Multiagent Systems · Computer Science 2025-05-27 Yifan Zhu , Chao Zhang , Xin Shi , Xueqiao Zhang , Yi Yang , Yawei Luo

Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety alignment and elicit harmful responses. A growing body of work shows that contextual priming, where earlier turns covertly bias later replies,…

Computation and Language · Computer Science 2026-05-05 Mario Rodríguez Béjar , Francisco J. Cortés-Delgado , S. Braghin , Jose L. Hernández-Ramos

Extended interaction with large language models (LLMs) has been linked to the reinforcement of delusional beliefs, a phenomenon attracting growing clinical and public concern. Yet most empirical work evaluates model safety in brief…

Human-Computer Interaction · Computer Science 2026-04-24 Luke Nicholls , Robert Hutto , Zephrah Soto , Hamilton Morrin , Thomas Pollak , Raj Korpan , Cheryl Carmichael

We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the…

Computation and Language · Computer Science 2019-04-02 Pushpendre Rastogi , Arpit Gupta , Tongfei Chen , Lambert Mathias
‹ Prev 1 3 4 5 6 7 10 Next ›