English
Related papers

Related papers: Collective Constitutional AI: Aligning a Language …

200 papers

A crucial consideration when developing and deploying Large Language Models (LLMs) is the human values to which these models are aligned. In the constitutional framework of alignment models are aligned to a set of principles (the…

Machine Learning · Computer Science 2026-01-27 Henry Bell , Lara Neubauer da Costa Schertel , Bochu Ding , Brandon Fain

Constitutional AI (CAI) guides LLM behavior using constitutions, but identifying which principles are most effective for model alignment remains an open challenge. We introduce the C3AI framework (\textit{Crafting Constitutions for CAI…

Artificial Intelligence · Computer Science 2025-02-25 Yara Kyrychenko , Ke Zhou , Edyta Bogucka , Daniele Quercia

Traditional methods for aligning Large Language Models (LLMs), such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on implicit principles, limiting interpretability. Constitutional AI…

Machine Learning · Computer Science 2025-04-01 Carl-Leander Henneking , Claas Beger

Constitutional AI is a method to oversee and control LLMs based on a set of rules written in natural language. These rules are typically written by human experts, but could in principle be learned automatically given sufficient training…

Artificial Intelligence · Computer Science 2026-03-18 Rushil Thareja , Gautam Gupta , Francesco Pinto , Nils Lukas

Constitutional AI (CAI) aligns language models with explicitly stated normative principles, offering a transparent alternative to implicit alignment through human feedback alone. However, because constitutions are authored by specific…

Computers and Society · Computer Science 2026-03-31 Parham Pourdavood

The growing capabilities of large language models (LLMs) have led to their use as substitutes for human feedback for training and assessing other LLMs. These methods often rely on `constitutions', written guidelines which a critic model…

Artificial Intelligence · Computer Science 2024-11-18 Saskia Redgate , Andrew M. Bean , Adam Mahdi

We are increasingly subjected to the power of AI authorities. As AI decisions become inescapable, entering domains such as healthcare, education, and law, we must confront a vital question: how can we ensure AI systems have the legitimacy…

Computers and Society · Computer Science 2025-05-15 Gilad Abiri

Large language models (LLMs) may not equitably represent diverse global perspectives on societal issues. In this paper, we develop a quantitative framework to evaluate whose opinions model-generated responses are more similar to. We first…

As language models continue to grow larger, the cost of acquiring high-quality training data has increased significantly. Collecting human feedback is both expensive and time-consuming, and manual labels can be noisy, leading to an…

Artificial Intelligence · Computer Science 2025-04-08 Xue Zhang

Large language models (LLMs) can support democratic deliberation at scales previously constrained by turn-taking and facilitation bandwidth. Recent work shows that LLM-generated group statements are often preferred over human-mediated…

Computation and Language · Computer Science 2026-05-27 Wajdi Zaghouani

Human feedback can prevent overtly harmful utterances in conversational models, but may not automatically mitigate subtle problematic behaviors such as a stated desire for self-preservation or power. Constitutional AI offers an alternative,…

Recent developments in Large Language Models (LLMs) have significantly expanded their applications across various domains. However, the effectiveness of LLMs is often constrained when operating individually in complex environments. This…

Artificial Intelligence · Computer Science 2024-05-08 Silvan Ferreira , Ivanovitch Silva , Allan Martins

With the growing adoption of AI systems, reasoning about how society can exert control over AI becomes an increasingly urgent problem. Existing work on democratic control largely focuses on macro-level governance. In contrast, we propose a…

Computers and Society · Computer Science 2026-05-19 Paul Anton Bachmann , Niclas Boehmer , Lukas Daniel Klausner , Martin Lackner

Traditional methods for eliciting people's opinions face a trade-off between depth and scale: structured surveys enable large-scale data collection but limit respondents' ability to voice their opinions in their own words, while…

Human-Computer Interaction · Computer Science 2025-03-13 Alexander Wuttke , Matthias Aßenmacher , Christopher Klamm , Max M. Lang , Quirin Würschinger , Frauke Kreuter

With the rapid development of large language models (LLMs), aligning LLMs with human values and societal norms to ensure their reliability and safety has become crucial. Reinforcement learning with human feedback (RLHF) and Constitutional…

Computation and Language · Computer Science 2024-03-28 Xiusi Chen , Hongzhi Wen , Sreyashi Nag , Chen Luo , Qingyu Yin , Ruirui Li , Zheng Li , Wei Wang

Community engagement processes form a critical foundation of democratic governance, yet frequently struggle with resource constraints, sensemaking challenges, and barriers to inclusive participation. These processes rely on constructive…

Human-Computer Interaction · Computer Science 2025-05-20 Cassandra Overney

Drawing from the resources of psychoanalysis and critical media studies, in this paper we develop an analysis of Large Language Models (LLMs) as automated subjects. We argue the intentional fictional projection of subjectivity onto LLMs can…

Computers and Society · Computer Science 2022-12-13 Liam Magee , Vanicka Arora , Luke Munn

As the societal implications of Artificial Intelligence (AI) continue to grow, the pursuit of responsible AI necessitates public engagement in its development and governance processes. This involvement is crucial for capturing diverse…

Computers and Society · Computer Science 2024-02-02 Necdet Gurkan , Jordan W. Suchow

Large language models (LLMs) have advanced the field of artificial intelligence (AI) and are a powerful enabler for interactive systems. However, they still face challenges in long-term interactions that require adaptation towards the user…

Artificial Intelligence · Computer Science 2025-05-20 Rebecca Westhäußer , Frederik Berenz , Wolfgang Minker , Sebastian Zepf

How AI models should deal with political topics has been discussed, but it remains challenging and requires better governance. This paper examines the governance of large language models through individual and collective deliberation,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Tanusree Sharma , Yujin Potter , Zachary Kilhoffer , Yun Huang , Dawn Song , Yang Wang
‹ Prev 1 2 3 10 Next ›