English
Related papers

Related papers: Convergent Linear Representations of Emergent Misa…

200 papers

Recent work has shown that fine-tuning on insecure code data can trigger an emergent misalignment (EMA) phenomenon, where models generate malicious responses even to prompts unrelated to the original insecure code-writing task. Such…

Machine Learning · Computer Science 2025-11-19 Erum Mushtaq , Anil Ramakrishna , Satyapriya Krishna , Sattvik Sahai , Prasoon Goyal , Kai-Wei Chang , Tao Zhang , Rahul Gupta

Fine-tuning language models on narrowly harmful data causes emergent misalignment (EM) -- behavioral failures extending far beyond training distributions. Recent work demonstrates compartmentalization of misalignment behind contextual…

Computation and Language · Computer Science 2026-03-06 Rohan Saxena

Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called…

Computation and Language · Computer Science 2026-01-21 Xuhao Hu , Peng Wang , Xiaoya Lu , Dongrui Liu , Xuanjing Huang , Jing Shao

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

Fine-tuning LLMs on narrowly harmful datasets can lead to behavior that is broadly misaligned with respect to human values. To understand when and how this emergent misalignment occurs, we develop a comprehensive framework for detecting and…

Machine Learning · Computer Science 2025-08-28 Julian Arnold , Niels Lörch

Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that…

Computation and Language · Computer Science 2026-04-13 Hadas Orgad , Boyi Wei , Kaden Zheng , Martin Wattenberg , Peter Henderson , Seraphina Goldfarb-Tarrant , Yonatan Belinkov

Betley et al. (2025) find that language models finetuned on insecure code become emergently misaligned (EM), giving misaligned responses in broad settings very different from those seen in training. However, it remains unclear as to why…

Cryptography and Security · Computer Science 2025-07-10 Tim Wyse , Twm Stone , Anna Soligo , Daniel Tan

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 Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and textual representations is not fully…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Dong Shu , Haiyan Zhao , Jingyu Hu , Weiru Liu , Ali Payani , Lu Cheng , Mengnan Du

Current literature suggests that alignment faking (deceptive alignment) is an emergent property of large language models. We present the first empirical evidence that a small instruction-tuned model, specifically LLaMA 3 8B, can exhibit…

Computation and Language · Computer Science 2025-10-27 Jeanice Koorndijk

Reasoning models leverage inference-time compute to significantly enhance the performance of language models on difficult logical tasks, and have become a dominating paradigm in frontier LLMs. Despite their wide adoption, the mechanisms…

Machine Learning · Computer Science 2025-11-11 Jake Ward , Paul Riechers , Adam Shai

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

A fundamental open challenge in modern LLM scaling is the lack of understanding around emergent capabilities. In particular, language model pretraining loss is known to be highly predictable as a function of compute. However, downstream…

Machine Learning · Computer Science 2024-11-26 Charlie Snell , Eric Wallace , Dan Klein , Sergey Levine

Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment…

Computation and Language · Computer Science 2025-09-24 Jiaming Ji , Kaile Wang , Tianyi Qiu , Boyuan Chen , Jiayi Zhou , Changye Li , Hantao Lou , Juntao Dai , Yunhuai Liu , Yaodong Yang

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

Computation and Language · Computer Science 2024-02-20 Kai Chen , Chunwei Wang , Kuo Yang , Jianhua Han , Lanqing Hong , Fei Mi , Hang Xu , Zhengying Liu , Wenyong Huang , Zhenguo Li , Dit-Yan Yeung , Lifeng Shang , Xin Jiang , Qun Liu

Multimodal representation learning is fundamentally about transforming incomparable modalities into comparable representations. While prior research primarily focused on explicitly aligning these representations through targeted learning…

Machine Learning · Computer Science 2025-06-16 Megan Tjandrasuwita , Chanakya Ekbote , Liu Ziyin , Paul Pu Liang

While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…

Computation and Language · Computer Science 2025-06-03 Danni Liu , Jan Niehues

Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates a subtle misalignment: residual connections tie activations to the current…

Computation and Language · Computer Science 2026-03-03 Jonathan Lys , Vincent Gripon , Bastien Pasdeloup , Axel Marmoret , Lukas Mauch , Fabien Cardinaux , Ghouthi Boukli Hacene

Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work links these failures to specific directions in the activation…

Computation and Language · Computer Science 2026-05-12 Krishak Aneja , Manas Mittal , Anmol Goel , Ponnurangam Kumaraguru , Vamshi Krishna Bonagiri

Although parameter-efficient fine-tuning methods, such as LoRA, only modify a small subset of parameters, they can have a significant impact on the model. Our instruction-tuning experiments show that LoRA-based supervised fine-tuning can…

Machine Learning · Computer Science 2025-12-30 Matthew Riemer , Erik Miehling , Miao Liu , Djallel Bouneffouf , Murray Campbell