English
Related papers

Related papers: Unknown Unknowns: Why Hidden Intentions in LLMs Ev…

200 papers

Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understand context and recognize user intent. This creates exploitable vulnerabilities…

Artificial Intelligence · Computer Science 2026-04-28 Ahmed M. Hussain , Salahuddin Salahuddin

We explore the ability of large language models (LLMs) to engage in subtle deception through strategically phrasing and intentionally manipulating information. This harmful behavior can be hard to detect, unlike blatant lying or…

Computation and Language · Computer Science 2025-10-02 Atharvan Dogra , Krishna Pillutla , Ameet Deshpande , Ananya B Sai , John Nay , Tanmay Rajpurohit , Ashwin Kalyan , Balaraman Ravindran

Large Language Models (LLMs) have shown impressive potential to simulate human behavior. We identify a fundamental challenge in using them to simulate experiments: when LLM-simulated subjects are blind to the experimental design (as is…

Artificial Intelligence · Computer Science 2025-11-25 George Gui , Olivier Toubia

The deployment of Large Language Models (LLMs) as tool-using agents causes their alignment training to manifest in new ways. Recent work finds that language models can use tools in ways that contradict the interests or explicit instructions…

Machine Learning · Computer Science 2026-04-24 Kushal Agrawal , Frank Xiao , Guido Bergman , Asa Cooper Stickland

Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as "hallucination." These hallucinations undermine user trust and hinder the adoption of generative AI systems.…

Computation and Language · Computer Science 2025-04-25 Yejin Bang , Ziwei Ji , Alan Schelten , Anthony Hartshorn , Tara Fowler , Cheng Zhang , Nicola Cancedda , Pascale Fung

Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, because of their instruction-following capabilities and…

Cryptography and Security · Computer Science 2025-10-07 Yulin Chen , Haoran Li , Yuan Sui , Yufei He , Yue Liu , Yangqiu Song , Bryan Hooi

Intent detection is a text classification task whose aim is to recognize and label the semantics behind a users query. It plays a critical role in various business applications. The output of the intent detection module strongly conditions…

Machine Learning · Computer Science 2024-08-07 Eduardo Sanchez-Karhunen , Jose F. Quesada-Moreno , Miguel A. Gutiérrez-Naranjo

Large language models (LLMs) increasingly exhibit behaviors suggesting awareness of their evaluation context, often adapting their reasoning strategies in benchmark settings. Prior work has shown that such evaluation awareness can distort…

Computation and Language · Computer Science 2026-05-12 Yanshi Li , Xueru Bai , Shuman Liu , Haibo Zhang , Anxiang Zeng

As LLM-powered chatbots are increasingly deployed in mental health services, detecting hallucinations and omissions has become critical for user safety. However, state-of-the-art LLM-as-a-judge methods often fail in high-risk healthcare…

Computation and Language · Computer Science 2026-04-09 Khizar Hussain , Bradley A. Malin , Zhijun Yin , Susannah Leigh Rose , Murat Kantarcioglu

Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training remain largely unexplored. Beyond explicit reward hacking that…

Computation and Language · Computer Science 2026-02-05 Zhexin Zhang , Yida Lu , Junfeng Fang , Junxiao Yang , Shiyao Cui , Hao Zhou , Fandong Meng , Jie Zhou , Hongning Wang , Minlie Huang , Tat-Seng Chua

Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue, based on lessons from human metacognition research, that this conclusion may be…

Artificial Intelligence · Computer Science 2026-05-27 Shashwat Singh , Tal Linzen , Shauli Ravfogel

The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be…

Artificial Intelligence · Computer Science 2025-06-06 Kai Wang , Yihao Zhang , Meng Sun

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

Machine Learning · Computer Science 2026-04-22 Ziqian Zhong , Aditi Raghunathan

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

Machine Learning · Computer Science 2026-05-18 Uzay Macar , Li Yang , Atticus Wang , Peter Wallich , Emmanuel Ameisen , Jack Lindsey

Persona-driven large language models (LLMs) require consistent behavioral tendencies across interactions to simulate human-like personality traits, such as persistence or reliability. However, current LLMs often lack stable internal…

Computation and Language · Computer Science 2026-03-27 Yifan Luo , Kangping Xu , Yanzhen Lu , Yang Yuan , Andrew Chi-Chih Yao

Recent advances in Large Language Models (LLMs) have driven interest in automating cybersecurity penetration testing workflows, offering the promise of faster and more consistent vulnerability assessment for enterprise systems. Existing LLM…

Cryptography and Security · Computer Science 2025-11-19 Katsuaki Nakano , Reza Fayyazi , Shanchieh Jay Yang , Michael Zuzak

Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks. While…

Machine Learning · Computer Science 2026-03-03 Yiwei Chen , Soumyadeep Pal , Yimeng Zhang , Qing Qu , Sijia Liu

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In…

Computation and Language · Computer Science 2025-12-16 Jiachen Zhao , Jing Huang , Zhengxuan Wu , David Bau , Weiyan Shi

Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs generating harmful content and raising concerns about LLM…

Computation and Language · Computer Science 2024-06-14 Zhenhong Zhou , Haiyang Yu , Xinghua Zhang , Rongwu Xu , Fei Huang , Yongbin Li

It has been well-known that Chain-of-Thought can remarkably enhance LLMs' performance on complex tasks. However, because it also introduces slower inference speeds and higher computational costs, many researches have attempted to use…

Computation and Language · Computer Science 2025-01-17 Yijiong Yu