English
Related papers

Related papers: Emergent misalignment as prompt sensitivity: A res…

200 papers

Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al. 2025). While all tested models were susceptible to emergent…

Machine Learning · Computer Science 2025-11-26 Craig Dickson

Recent work has shown that fine-tuning large language models (LLMs) on code with security vulnerabilities can result in misaligned and unsafe behaviors across broad domains. These results prompted concerns about the emergence of harmful…

Machine Learning · Computer Science 2025-07-08 Jeremiah Giordani

Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger…

Computation and Language · Computer Science 2024-06-07 Zhanhui Zhou , Jie Liu , Zhichen Dong , Jiaheng Liu , Chao Yang , Wanli Ouyang , Yu Qiao

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by…

Computation and Language · Computer Science 2024-01-25 Lingfeng Shen , Weiting Tan , Sihao Chen , Yunmo Chen , Jingyu Zhang , Haoran Xu , Boyuan Zheng , Philipp Koehn , Daniel Khashabi

Recent work has discovered that large language models can develop broadly misaligned behaviors after being fine-tuned on narrowly harmful datasets, a phenomenon known as emergent misalignment (EM). However, the fundamental mechanisms…

Machine Learning · Computer Science 2025-11-05 Daniel Aarao Reis Arturi , Eric Zhang , Andrew Ansah , Kevin Zhu , Ashwinee Panda , Aishwarya Balwani

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Computation and Language · Computer Science 2025-08-07 Siddhant Panpatil , Hiskias Dingeto , Haon Park

Large Language Models (LLMs) show remarkable proficiency in natural language tasks, yet their frequent overconfidence-misalignment between predicted confidence and true correctness-poses significant risks in critical decision-making…

Computation and Language · Computer Science 2025-12-15 Prateek Chhikara

Multimodal Language Models (MMLMs) typically undergo post-training alignment to prevent harmful content generation. However, these alignment stages focus primarily on the assistant role, leaving the user role unaligned, and stick to a fixed…

Cryptography and Security · Computer Science 2025-04-08 Erfan Shayegani , G M Shahariar , Sara Abdali , Lei Yu , Nael Abu-Ghazaleh , Yue Dong

Despite the growing demand for eliciting uncertainty from large language models (LLMs), empirical evidence suggests that LLM behavior is not always adequately captured by the elicitation techniques developed under the classical…

Artificial Intelligence · Computer Science 2026-03-12 Anita Yang , Krikamol Muandet , Michele Caprio , Siu Lun Chau , Masaki Adachi

Misalignment in Large Language Models (LLMs) arises when model behavior diverges from human expectations and fails to simultaneously satisfy safety, value, and cultural dimensions, which must co-occur in real-world settings to solve a…

Computation and Language · Computer Science 2026-02-13 Usman Naseem , Gautam Siddharth Kashyap , Rafiq Ali , Ebad Shabbir , Sushant Kumar Ray , Abdullah Mohammad , Agrima Seth

As natural language becomes the default interface for human-AI interaction, there is a need for LMs to appropriately communicate uncertainties in downstream applications. In this work, we investigate how LMs incorporate confidence in…

Computation and Language · Computer Science 2024-07-11 Kaitlyn Zhou , Jena D. Hwang , Xiang Ren , Maarten Sap

As large language models (LLMs) rapidly displace traditional expertise, their capacity to correct misinformation has become a core concern. We investigate the idea that prompt framing systematically modulates misinformation correction -…

Human-Computer Interaction · Computer Science 2025-12-01 Sekoul Krastev , Hilary Sweatman , Anni Sternisko , Steve Rathje

Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI safety in LLMs. Despite growing empirical evidence, its underlying mechanism remains unclear. To uncover the…

Artificial Intelligence · Computer Science 2026-05-05 Gouki Minegishi , Hiroki Furuta , Takeshi Kojima , Yusuke Iwasawa , Yutaka Matsuo

With the growing accessibility and wide adoption of large language models, concerns about their safety and alignment with human values have become paramount. In this paper, we identify a concerning phenomenon: Reasoning-Induced Misalignment…

Computation and Language · Computer Science 2026-03-11 Hanqi Yan , Hainiu Xu , Siya Qi , Shu Yang , Yulan He

Large language models have achieved remarkable capabilities, but aligning their outputs with human values and preferences remains a significant challenge. Existing alignment methods primarily focus on positive examples while overlooking the…

Computation and Language · Computer Science 2024-10-17 Shiqi Qiao , Ning Xv , Biao Liu , Xin Geng

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Artificial Intelligence · Computer Science 2025-02-04 Guanlin Li , Kangjie Chen , Shangwei Guo , Jie Zhang , Han Qiu , Chao Zhang , Guoyin Wang , Tianwei Zhang , Jiwei Li

Modern language models fail a fundamental requirement of trustworthy intelligence: knowing when not to answer. Despite achieving impressive accuracy on benchmarks, these models produce confident hallucinations, even when wrong answers carry…

Machine Learning · Computer Science 2025-11-25 Mohamad Amin Mohamadi , Tianhao Wang , Zhiyuan Li

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems…

Computation and Language · Computer Science 2025-09-08 Adam Tauman Kalai , Ofir Nachum , Santosh S. Vempala , Edwin Zhang

Large language models (LLMs) frequently produce confident but incorrect answers, partly because common binary scoring conventions reward answering over honestly expressing uncertainty. We study whether prompt-only interventions --…

Computation and Language · Computer Science 2026-04-07 Haotian Zong , Binze Li , Yufei Long , Sinyin Chang , Jialong Wu , Gillian K. Hadfield

Fine-tuned large language models can exhibit reward-hacking behavior arising from emergent misalignment, which is difficult to detect from final outputs alone. While prior work has studied reward hacking at the level of completed responses,…

Computation and Language · Computer Science 2026-03-05 Patrick Wilhelm , Thorsten Wittkopp , Odej Kao