English
Related papers

Related papers: Simulating the Evolution of Alignment and Values i…

200 papers

Value alignment is the task of creating autonomous systems whose values align with those of humans. Past work has shown that stories are a potentially rich source of information on human values; however, past work has been limited to…

Computation and Language · Computer Science 2022-12-13 Md Sultan Al Nahian , Spencer Frazier , Brent Harrison , Mark Riedl

Machine learning models trained on real-world data may inadvertently make biased predictions that negatively impact marginalized communities. Reweighting, which assigns a weight to each data point used during model training, can mitigate…

Machine Learning · Computer Science 2026-03-20 Anil K. Saini , Jose Guadalupe Hernandez , Emily F. Wong , Debanshi Misra , Tiffani J. Bright , Jason H. Moore

How can researchers identify beliefs that large language models (LLMs) hide? As LLMs become more sophisticated and the prevalence of alignment faking increases, combined with their growing integration into high-stakes decision-making,…

Computers and Society · Computer Science 2026-02-26 Maxim Chupilkin

Machine learning models are essential tools in various domains, but their performance can degrade over time due to changes in data distribution or other factors. On one hand, detecting and addressing such degradations is crucial for…

Machine Learning · Computer Science 2023-09-28 Florian Heinrichs

Word evolution refers to the changing meanings and associations of words throughout time, as a byproduct of human language evolution. By studying word evolution, we can infer social trends and language constructs over different periods of…

Computation and Language · Computer Science 2018-02-14 Zijun Yao , Yifan Sun , Weicong Ding , Nikhil Rao , Hui Xiong

Large language models implicitly encode preferences over human values, yet steering them often requires large training data. In this work, we investigate a simple approach: Can we reliably modify a model's value system in downstream…

Computation and Language · Computer Science 2025-08-18 Shangrui Nie , Florian Mai , David Kaczér , Charles Welch , Zhixue Zhao , Lucie Flek

The field of AI alignment aims to steer AI systems toward human goals, preferences, and ethical principles. Its contributions have been instrumental for improving the output quality, safety, and trustworthiness of today's AI models. This…

Artificial Intelligence · Computer Science 2024-11-26 Robert West , Roland Aydin

Although pretrained language models (PTLMs) have been shown to contain significant amounts of world knowledge, they can still produce inconsistent answers to questions when probed, even after using specialized training techniques to reduce…

Computation and Language · Computer Science 2021-10-08 Nora Kassner , Oyvind Tafjord , Hinrich Schutze , Peter Clark

Machine intelligence can develop either directly from experience or by inheriting experience through evolution. The bulk of current research efforts focus on algorithms which learn directly from experience. I argue that the alternative,…

Neural and Evolutionary Computing · Computer Science 2021-06-22 Awni Hannun

As AI systems advance beyond human capabilities, scalable oversight becomes critical: how can we supervise AI that exceeds our abilities? A key challenge is that human evaluators may form incorrect beliefs about AI behavior in complex…

Artificial Intelligence · Computer Science 2025-10-22 Leon Lang , Patrick Forré

Confirmation bias is a cognitive bias that adversely affects management decisions, and mathematical modelling is an aid to its detailed understanding. Bias in opinion update about the value of a parameter is modelled here assuming that…

Other Statistics · Statistics 2022-02-08 Rose D Baker

Machine unlearning, an emerging research topic focusing on compliance with data privacy regulations, enables trained models to remove the information learned from specific data. While many existing methods indirectly address this issue by…

Machine Learning · Computer Science 2024-12-24 Seonguk Seo , Dongwan Kim , Bohyung Han

Researchers in social science and psychology have recently proposed using large language models (LLMs) as replacements for humans in behavioral research. In addition to arguments about whether LLMs accurately capture population-level…

Computation and Language · Computer Science 2025-07-09 Sonia K. Murthy , Tomer Ullman , Jennifer Hu

Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete.…

Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of…

Machine Learning · Computer Science 2022-05-19 Akihito Yoshii , Susumu Tokumoto , Fuyuki Ishikawa

Whenever an AI model is used to predict a relevant (binary) outcome in AI-assisted decision making, it is widely agreed that, together with each prediction, the model should provide an AI confidence value. However, it has been unclear why…

Artificial Intelligence · Computer Science 2025-01-27 Nina L. Corvelo Benz , Manuel Gomez Rodriguez

When a prediction algorithm serves a collection of users, disparities in prediction quality are likely to emerge. If users respond to accurate predictions by increasing engagement, inviting friends, or adopting trends, repeated learning…

Machine Learning · Computer Science 2025-11-27 Eden Saig , Nir Rosenfeld

Machine learning (ML) models are increasingly being used in metrology applications. However, for ML models to be credible in a metrology context they should be accompanied by principled uncertainty quantification. This paper addresses the…

Machine Learning · Computer Science 2024-05-09 Andrew Thompson

Background: Value alignment in computer science research is often used to refer to the process of aligning artificial intelligence with humans, but the way the phrase is used often lacks precision. Objectives: In this paper, we conduct a…

Computers and Society · Computer Science 2026-03-27 Jack McKinlay , Marina De Vos , Janina A. Hoffmann , Andreas Theodorou

Using a time series model to mimic an observed time series has a long history. However, with regard to this objective, conventional estimation methods for discrete-time dynamical models are frequently found to be wanting. In fact, they are…

Statistics Theory · Mathematics 2015-03-19 Yingcun Xia , Howell Tong