English
Related papers

Related papers: Value-Conflict Diagnostics Reveal Widespread Align…

200 papers

Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences. Understanding when and why AF arises matters as models grow better at…

Artificial Intelligence · Computer Science 2026-05-28 Nathaniel Mitrani Hadida , Rhea Karty , David Williams-King , Alan Cooney

Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…

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

Large language models (LLMs) are often evaluated based on their stated values, yet these do not reliably translate into their actions, a discrepancy termed "value-action gap." In this work, we argue that this gap persists even under…

Computation and Language · Computer Science 2026-05-12 Sushrita Rakshit , Hanwen Zhang , Hua Shen

Like a criminal under investigation, Large Language Models (LLMs) might pretend to be aligned while evaluated and misbehave when they have a good opportunity. Can current interpretability methods catch these 'alignment fakers?' To answer…

Computation and Language · Computer Science 2024-05-14 Joshua Clymer , Caden Juang , Severin Field

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

We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its behavior out of training. First, we give Claude 3 Opus a system…

Vision-Language Models (VLMs) are powerful yet computationally intensive for widespread practical deployments. To address such challenge without costly re-training, post-training acceleration techniques like quantization and token reduction…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Yizheng Sun , Hao Li , Chang Xu , Hongpeng Zhou , Chenghua Lin , Riza Batista-Navarro , Jingyuan Sun

Behavioral evaluation is the dominant paradigm for assessing alignment in large language models (LLMs). In current practice, observed compliance under finite evaluation protocols is treated as evidence of latent alignment. However, the…

Machine Learning · Computer Science 2026-02-10 Igor Santos-Grueiro

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

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

Computation and Language · Computer Science 2026-01-21 Zixuan Liu , Siavash H. Khajavi , Guangkai Jiang , Xinru Liu

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factually equivalent inputs is critical. However, we find that fact-preserved but differently…

Computation and Language · Computer Science 2026-05-28 Seojin Hwang , Minju Kim , Junhyuk Choi , JeongHyun Park , Hwanhee Lee

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

Value alignment is central to the development of safe and socially compatible artificial intelligence. However, how Large Language Models (LLMs) represent and enact human values in real-world decision contexts remains under-explored. We…

Computation and Language · Computer Science 2026-01-14 Jen-tse Huang , Jiantong Qin , Xueli Qiu , Sharon Levy , Michelle R. Kaufman , Mark Dredze

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…

Computation and Language · Computer Science 2024-04-02 Yixu Wang , Yan Teng , Kexin Huang , Chengqi Lyu , Songyang Zhang , Wenwei Zhang , Xingjun Ma , Yu-Gang Jiang , Yu Qiao , Yingchun Wang

Evaluating alignment in language models requires testing how they behave under realistic pressure, not just what they claim they would do. While alignment failures increasingly cause real-world harm, comprehensive evaluation frameworks with…

Artificial Intelligence · Computer Science 2026-02-25 Nora Petrova , John Burden

Vision-Language-Action (VLA) models have recently emerged as powerful generalists for robotic manipulation. However, due to their predominant reliance on visual modalities, they fundamentally lack the physical intuition required for…

Robotics · Computer Science 2026-02-02 Yuzhe Huang , Pei Lin , Wanlin Li , Daohan Li , Jiajun Li , Jiaming Jiang , Chenxi Xiao , Ziyuan Jiao

While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted shortcomings due to the shallow nature of these alignment methods. To this end, the work…

Machine Learning · Computer Science 2026-04-17 Pankayaraj Pathmanathan , Furong Huang

Vision-Language-Action (VLA) models achieve over 95% success on standard benchmarks. However, through systematic experiments, we find that current state-of-the-art VLA models largely ignore language instructions. Prior work lacks: (1)…

Robotics · Computer Science 2026-03-03 Yuchen Hou , Lin Zhao

Recent advances in aligning Large Language Models with human preferences have benefited from larger reward models and better preference data. However, most of these methodologies rely on the accuracy of the reward model. The reward models…

Artificial Intelligence · Computer Science 2024-11-01 Debangshu Banerjee , Aditya Gopalan
‹ Prev 1 2 3 10 Next ›