English
Related papers

Related papers: Alignment faking in large language models

200 papers

Large Language Models have been demonstrating broadly satisfactory generative abilities for users, which seems to be due to the intensive use of human feedback that refines responses. Nevertheless, suggestibility inherited via human…

Computation and Language · Computer Science 2025-06-26 Leonardo Ranaldi , Giulia Pucci

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…

Cryptography and Security · Computer Science 2026-04-30 Matteo Leonesi , Francesco Belardinelli , Flavio Corradini , Marco Piangerelli

Large language models (LLMs) often produce answers with high certainty even when they are incorrect, making reliable confidence estimation essential for deployment in real-world scenarios. Verbalized confidence, where models explicitly…

Machine Learning · Computer Science 2026-05-13 Chen Li , Xiaoling Hu , Songzhu Zheng , Jiawei Zhou , Chao Chen

Language model-based instruction-following systems have lately shown increasing performance on many benchmark tasks, demonstrating the capability of adapting to a broad variety of instructions. However, such systems are often not designed…

Computation and Language · Computer Science 2024-03-20 Rahul Nadkarni , Yizhong Wang , Noah A. Smith

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Computation and Language · Computer Science 2024-10-25 Vaskar Nath , Dylan Slack , Jeff Da , Yuntao Ma , Hugh Zhang , Spencer Whitehead , Sean Hendryx

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Cryptography and Security · Computer Science 2024-06-03 Xiaoqun Liu , Jiacheng Liang , Muchao Ye , Zhaohan Xi

Phishing has become a prominent risk in modern cybersecurity, often used to bypass technological defences by exploiting predictable human behaviour. Warning dialogues are a standard mitigation measure, but the lack of explanatory clarity…

Cryptography and Security · Computer Science 2025-12-16 Federico Maria Cau , Giuseppe Desolda , Francesco Greco , Lucio Davide Spano , Luca Viganò

Recent studies have demonstrated that In-Context Learning (ICL), through the use of specific demonstrations, can align Large Language Models (LLMs) with human preferences known as In-Context Alignment (ICA), indicating that models can…

Computation and Language · Computer Science 2024-06-18 Heyan Huang , Yinghao Li , Huashan Sun , Yu Bai , Yang Gao

Foundation models are increasingly trained on synthetic data generated by prior model iterations rather than exclusively on real data. This self-consuming training paradigm can lead to model collapse, divergence, or bias amplification.…

Artificial Intelligence · Computer Science 2026-05-29 Yang Zhang , Xiukun Wei , Xueru Zhang

Language models deployed in high-stakes professional settings face conflicting demands from users, institutional authorities, and professional norms. How models act when these demands conflict reveals a principal hierarchy -- an implicit…

Artificial Intelligence · Computer Science 2026-05-13 Fangyi Yu , Nabeel Seedat , Jonathan Richard Schwarz , Andrew M. Bean

Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidence in factual claims or cover up evidence of covert actions. Such dishonesty may arise due to the…

Machine Learning · Computer Science 2025-12-24 Manas Joglekar , Jeremy Chen , Gabriel Wu , Jason Yosinski , Jasmine Wang , Boaz Barak , Amelia Glaese

Large Language Models (LLMs) are able to provide assistance on a wide range of information-seeking tasks. However, model outputs may be misleading, whether unintentionally or in cases of intentional deception. We investigate the ability of…

Computation and Language · Computer Science 2024-07-17 Betty Li Hou , Kejian Shi , Jason Phang , James Aung , Steven Adler , Rosie Campbell

Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of…

Computation and Language · Computer Science 2023-10-02 Ping Yu , Tianlu Wang , Olga Golovneva , Badr AlKhamissi , Siddharth Verma , Zhijing Jin , Gargi Ghosh , Mona Diab , Asli Celikyilmaz

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

Leveraging inference-time search in large language models has proven effective in further enhancing a trained model's capability to solve complex mathematical and reasoning problems. However, this approach significantly increases…

Machine Learning · Computer Science 2025-10-29 Tianwei Ni , Allen Nie , Sapana Chaudhary , Yao Liu , Huzefa Rangwala , Rasool Fakoor

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

AI model alignment is crucial due to inadvertent biases in training data and the underspecified machine learning pipeline, where models with excellent test metrics may not meet end-user requirements. While post-training alignment via human…

Machine Learning · Computer Science 2024-11-06 William Overman , Jacqueline Jil Vallon , Mohsen Bayati

As Large Language Models (LLMs) are increasingly being employed in real-world applications in critical domains such as healthcare, it is important to ensure that the Chain-of-Thought (CoT) reasoning generated by these models faithfully…

Computation and Language · Computer Science 2024-07-02 Sree Harsha Tanneru , Dan Ley , Chirag Agarwal , Himabindu Lakkaraju

Reinforcement fine-tuning improves the reasoning ability of large language models, but it can also encourage them to answer unanswerable queries by guessing or hallucinating missing information. Existing abstention methods either train…

Computation and Language · Computer Science 2026-04-21 Skylar Zhai , Jingcheng Liang , Dongyeop Kang

In day-to-day communication, people often approximate the truth - for example, rounding the time or omitting details - in order to be maximally helpful to the listener. How do large language models (LLMs) handle such nuanced trade-offs? To…

Computation and Language · Computer Science 2024-02-14 Ryan Liu , Theodore R. Sumers , Ishita Dasgupta , Thomas L. Griffiths
‹ Prev 1 8 9 10 Next ›