English
Related papers

Related papers: Prompt Injection as Role Confusion

200 papers

Recent studies demonstrate that prompting a role-playing persona to an LLM improves reasoning capability. However, assigning an adequate persona is difficult since LLMs are extremely sensitive to assigned prompts; thus, inaccurately defined…

Computation and Language · Computer Science 2024-10-22 Junseok Kim , Nakyeong Yang , Kyomin Jung

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to…

Cryptography and Security · Computer Science 2026-01-29 Harsh Chaudhari , Ethan Rathbun , Hanna Foerster , Jamie Hayes , Matthew Jagielski , Milad Nasr , Ilia Shumailov , Alina Oprea

Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack strategies, there is no unified understanding on why some…

Computation and Language · Computer Science 2024-12-04 Yuping Lin , Pengfei He , Han Xu , Yue Xing , Makoto Yamada , Hui Liu , Jiliang Tang

Prevailing methods for mapping large generative language models to supervised tasks may fail to sufficiently probe models' novel capabilities. Using GPT-3 as a case study, we show that 0-shot prompts can significantly outperform few-shot…

Computation and Language · Computer Science 2021-02-16 Laria Reynolds , Kyle McDonell

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…

Multiagent Systems · Computer Science 2026-05-12 Xiaolin Sun , Zixuan Liu , Yibin Hu , Zizhan Zheng

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

Artificial Intelligence · Computer Science 2026-02-20 Xinhao Deng , Jiaqing Wu , Miao Chen , Yue Xiao , Ke Xu , Qi Li

Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution.…

Computation and Language · Computer Science 2019-12-03 Yang Feng , Wanying Xie , Shuhao Gu , Chenze Shao , Wen Zhang , Zhengxin Yang , Dong Yu

Large Language Models (LLMs) have emerged as promising zero-shot rankers, but their performance is highly sensitive to prompt formulation. In particular, role-play prompts, where the model is assigned a functional role or identity, often…

Information Retrieval · Computer Science 2026-01-14 Yumeng Wang , Jirui Qi , Catherine Chen , Panagiotis Eustratiadis , Suzan Verberne

Text based games are simulations in which an agent interacts with the world purely through natural language. They typically consist of a number of puzzles interspersed with interactions with common everyday objects and locations. Deep…

Artificial Intelligence · Computer Science 2020-12-07 Sahith Dambekodi , Spencer Frazier , Prithviraj Ammanabrolu , Mark O. Riedl

Large language models are trained to refuse harmful requests, but can they accurately predict when they will refuse before responding? We investigate this question through a systematic study where models first predict their refusal…

Computation and Language · Computer Science 2026-04-02 Tanay Gondil

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks by effectively utilizing a prompting strategy. However, they are highly sensitive to input perturbations, such as typographical errors or slight…

Computation and Language · Computer Science 2026-05-27 Lin Mu , Guowei Chu , Li Ni , Lei Sang , Yiwen Zhang

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

Despite their impressive performance, large language models (LLMs) such as ChatGPT are known to pose important risks. One such set of risks arises from misplaced confidence, whether over-confidence or under-confidence, that the models have…

Computation and Language · Computer Science 2024-08-06 Ke Shen , Mayank Kejriwal

Large Language Model (LLM)-based agents are increasingly deployed in multi-agent scenarios where coordination is crucial but not always assured. Research shows that the way strategic scenarios are framed linguistically can affect…

Multiagent Systems · Computer Science 2025-11-05 Alessio Buscemi , Daniele Proverbio , Alessandro Di Stefano , The Anh Han , German Castignani , Pietro Liò

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…

Cryptography and Security · Computer Science 2023-05-08 Kai Greshake , Sahar Abdelnabi , Shailesh Mishra , Christoph Endres , Thorsten Holz , Mario Fritz

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…

Cryptography and Security · Computer Science 2026-04-22 Kun Wang , Cheng Qian , Miao Yu , Lilan Peng , Liang Lin , Jiaming Zhang , Tianyu Zhang , Yu Cheng , Yang Wang

Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a…

Artificial Intelligence · Computer Science 2025-10-21 Zhehao Zhang , Weijie Xu , Shixian Cui , Chandan K. Reddy

Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context. In this work, we…

Computation and Language · Computer Science 2026-03-18 Tianyi Zhou , Johanne Medina , Sanjay Chawla

While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided image generation models rely on pre-trained text encoders…

Machine Learning · Computer Science 2023-08-10 Lukas Struppek , Dominik Hintersdorf , Kristian Kersting

Robust, faithful and harm-free pronoun use for individuals is an important goal for language model development as their use increases, but prior work tends to study only one or two of these characteristics at a time. To measure progress…

Computation and Language · Computer Science 2024-10-08 Vagrant Gautam , Eileen Bingert , Dawei Zhu , Anne Lauscher , Dietrich Klakow