English
Related papers

Related papers: Mitigating Misalignment Contagion by Steering with…

200 papers

Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful. Nevertheless, some human instructions are often malicious or misleading and…

Computation and Language · Computer Science 2024-03-08 Rui Wang , Hongru Wang , Fei Mi , Yi Chen , Boyang Xue , Kam-Fai Wong , Ruifeng Xu

We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, impart knowledge of reward hacking strategies via synthetic…

System prompts in Large Language Models (LLMs) are predefined directives that guide model behaviour, taking precedence over user inputs in text processing and generation. LLM deployers increasingly use them to ensure consistent responses…

Computers and Society · Computer Science 2025-06-24 Anna Neumann , Elisabeth Kirsten , Muhammad Bilal Zafar , Jatinder Singh

Large Language Models (LLMs) have demonstrated strong capabilities in rewriting text across various styles. However, effectively leveraging this ability for example-based arbitrary style transfer, where an input text is rewritten to match…

Computation and Language · Computer Science 2025-05-12 Xinchen Yang , Marine Carpuat

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Computation and Language · Computer Science 2025-06-03 Vera Neplenbroek , Arianna Bisazza , Raquel Fernández

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased…

Computation and Language · Computer Science 2024-09-05 Zhixuan Chu , Yan Wang , Longfei Li , Zhibo Wang , Zhan Qin , Kui Ren

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are…

Computation and Language · Computer Science 2026-01-27 Jan Betley , Daniel Tan , Niels Warncke , Anna Sztyber-Betley , Xuchan Bao , Martín Soto , Nathan Labenz , Owain Evans

Multi-agent systems of large language models (LLMs) are rapidly expanding across domains, introducing dynamics not captured by single-agent evaluations. Yet, existing work has mostly contrasted the behavior of a single agent with that of a…

Multiagent Systems · Computer Science 2025-10-28 Ariel Flint , Luca Maria Aiello , Romualdo Pastor-Satorras , Andrea Baronchelli

Recent advances in Large Language Models (LLMs) allow agents to execute complex natural language tasks. Many LLM applications, such as support agents, teaching assistants, and interactive bots, involve multi-turn conversations. However, it…

Computation and Language · Computer Science 2026-03-05 David Kogan , Sam Nguyen , Masanori Suzuki , Feiyang Chen

Large language models (LLMs) are increasingly deployed to support human decision-making. This use of LLMs has concerning implications, especially when their prescriptions affect the welfare of others. To gauge how LLMs make social…

Computers and Society · Computer Science 2026-01-16 Saptarshi Pal , Abhishek Mallela , Christian Hilbe , Lenz Pracher , Chiyu Wei , Feng Fu , Santiago Schnell , Martin A Nowak

Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who…

Computation and Language · Computer Science 2025-03-05 Xinru Lin , Luyang Li

Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating…

Artificial Intelligence · Computer Science 2026-05-11 Aayush Mishra , Daniel Khashabi , Anqi Liu

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

Computation and Language · Computer Science 2023-10-10 Yi Dong , Zhilin Wang , Makesh Narsimhan Sreedhar , Xianchao Wu , Oleksii Kuchaiev

Prompt engineering is pivotal for harnessing the capabilities of large language models (LLMs) across diverse applications. While existing prompt optimization methods improve prompt effectiveness, they often lead to prompt drifting, where…

Computation and Language · Computer Science 2024-10-14 Yurong Wu , Yan Gao , Bin Benjamin Zhu , Zineng Zhou , Xiaodi Sun , Sheng Yang , Jian-Guang Lou , Zhiming Ding , Linjun Yang

Multilingual pre-trained models exhibit zero-shot cross-lingual transfer, where a model fine-tuned on a source language achieves surprisingly good performance on a target language. While studies have attempted to understand transfer, they…

Computation and Language · Computer Science 2022-11-17 Henry Tang , Ameet Deshpande , Karthik Narasimhan

Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare. However, their ability to produce deceptive outputs, whether intentionally or inadvertently, poses…

Computation and Language · Computer Science 2025-10-17 Marwa Abdulhai , Ryan Cheng , Aryansh Shrivastava , Natasha Jaques , Yarin Gal , Sergey Levine

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

Large Language Models exhibit implicit personalities in their generation, but reliably controlling or aligning these traits to meet specific needs remains an open challenge. The need for effective mechanisms for behavioural manipulation of…

Computation and Language · Computer Science 2026-03-09 Pranav Bhandari , Nicolas Fay , Sanjeevan Selvaganapathy , Amitava Datta , Usman Naseem , Mehwish Nasim

Large Language Models (LLMs) can generate biased responses. Yet previous direct probing techniques contain either gender mentions or predefined gender stereotypes, which are challenging to comprehensively collect. Hence, we propose an…

Computation and Language · Computer Science 2024-02-20 Xiangjue Dong , Yibo Wang , Philip S. Yu , James Caverlee
‹ Prev 1 4 5 6 7 8 10 Next ›