English
Related papers

Related papers: Inverse Constitutional AI: Compressing Preferences…

200 papers

Recent empirical results have demonstrated that training large language models (LLMs) with negative-only feedback can match or exceed standard reinforcement learning from human feedback (RLHF). Negative Sample Reinforcement achieves parity…

Artificial Intelligence · Computer Science 2026-03-18 Quan Cheng

Transformative AI systems may pose unprecedented catastrophic risks, but the U.S. Constitution places significant constraints on the government's ability to govern this technology. This paper examines how the First Amendment, administrative…

Computers and Society · Computer Science 2025-12-19 Alex Mark , Aaron Scher

AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when…

Artificial Intelligence · Computer Science 2026-04-14 Behrooz Razeghi

Voting rules based on evaluation inputs rather than preference orders have been recently proposed, like majority judgement, range voting or approval voting. Traditionally, probabilistic analysis of voting rules supposes the use of…

Artificial Intelligence · Computer Science 2021-04-19 Antoine Rolland , Jean-Baptiste Aubin , Irène Gannaz , Samuela Leoni

Frontier AI developers now train models against long written behavioral specifications, such as Anthropic's constitution (Anthropic, 2025a) and OpenAI's Model Spec (OpenAI, 2025a), integrated into post-training via methods like character…

Artificial Intelligence · Computer Science 2026-05-26 Arya Jakkli , Senthooran Rajamanoharan , Neel Nanda

We introduce a black-box interpretability framework that learns a verifiable constitution: a natural language summary of how changes to a prompt affect a model's specific behavior, such as its alignment, correctness, or adherence to…

Machine Learning · Computer Science 2026-02-03 Neha Kalibhat , Zi Wang , Prasoon Bajpai , Drew Proud , Wenjun Zeng , Been Kim , Mani Malek

Predicting agents impacted by legal policies, physical limitations, and operational preferences is inherently difficult. In recent years, neuro-symbolic methods have emerged, integrating machine learning and symbolic reasoning models into…

Aggregating preferences under incomplete or constrained feedback is a fundamental problem in social choice and related domains. While prior work has established strong impossibility results for pairwise comparisons, this paper extends the…

Computer Science and Game Theory · Computer Science 2025-02-19 Evi Micha , Vasilis Varsamis

Preference learning is critical for aligning large language models (LLMs) with human values, yet its success hinges on high-quality datasets comprising three core components: Preference \textbf{A}nnotations, \textbf{I}nstructions, and…

Computation and Language · Computer Science 2025-09-03 Bingxiang He , Wenbin Zhang , Jiaxi Song , Cheng Qian , Zixuan Fu , Bowen Sun , Ning Ding , Haiwen Hong , Longtao Huang , Hui Xue , Ganqu Cui , Wanxiang Che , Zhiyuan Liu , Maosong Sun

Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the quality of positive…

Computation and Language · Computer Science 2023-05-23 Qinyuan Cheng , Xiaogui Yang , Tianxiang Sun , Linyang Li , Xipeng Qiu

Aligning large language models (LLMs) with human values and intents critically involves the use of human or AI feedback. While dense feedback annotations are expensive to acquire and integrate, sparse feedback presents a structural design…

Machine Learning · Computer Science 2024-02-07 Hritik Bansal , John Dang , Aditya Grover

We explore the idea of aligning an AI assistant by inverting a model of users' (unknown) preferences from observed interactions. To validate our proposal, we run proof-of-concept simulations in the economic ultimatum game, formalizing user…

Computation and Language · Computer Science 2023-12-05 Jan-Philipp Fränken , Sam Kwok , Peixuan Ye , Kanishk Gandhi , Dilip Arumugam , Jared Moore , Alex Tamkin , Tobias Gerstenberg , Noah D. Goodman

The constitutional framework of alignment aims to align large language models (LLMs) with value-laden principles written in natural language (such as to avoid using biased language). Prior work has focused on parameter fine-tuning…

Computation and Language · Computer Science 2026-01-27 Henry Bell , Caroline Zhang , Mohammed Mobasserul Haque , Dhaval Potdar , Samia Zaman , Brandon Fain

Given that Artificial Intelligence (AI) increasingly permeates our lives, it is critical that we systematically align AI objectives with the goals and values of humans. The human-AI alignment problem stems from the impracticality of…

Computers and Society · Computer Science 2022-07-05 John Nay , James Daily

In aligning large language models (LLMs), utilizing feedback from existing advanced AI rather than humans is an important method to scale supervisory signals. However, it is highly challenging for AI to understand human intentions and…

Computation and Language · Computer Science 2024-06-18 Rong Bao , Rui Zheng , Shihan Dou , Xiao Wang , Enyu Zhou , Bo Wang , Qi Zhang , Liang Ding , Dacheng Tao

Decision analysis deals with modeling and enhancing decision processes. A principal challenge in improving behavior is in obtaining a transparent description of existing behavior in the first place. In this paper, we develop an expressive,…

Machine Learning · Statistics 2023-10-31 Daniel Jarrett , Alihan Hüyük , Mihaela van der Schaar

Large language model (LLM) prompting is a promising new approach for users to create and customize their own chatbots. However, current methods for steering a chatbot's outputs, such as prompt engineering and fine-tuning, do not support…

Human-Computer Interaction · Computer Science 2023-10-25 Savvas Petridis , Ben Wedin , James Wexler , Aaron Donsbach , Mahima Pushkarna , Nitesh Goyal , Carrie J. Cai , Michael Terry

Preference-based argumentation frameworks (PAFs) extend Dung's approach to abstract argumentation (AAFs) by encoding preferences over arguments. Such preferences control the transformation of attacks into defeats, and different approaches…

Artificial Intelligence · Computer Science 2026-04-28 Alessio Zaninotto , Bruno Yun , Nir Oren , Srdjan Vesic

Preference-based reinforcement learning (PbRL) is the dominant framework for aligning AI systems to human preferences. However, evaluation protocols for such data were designed for text and have not been validated for speech. We present the…

Sound · Computer Science 2026-05-08 Aaron Broukhim , Nadir Weibel , Eshin Jolly

Building artificial intelligence (AI) that aligns with human values is an unsolved problem. Here, we developed a human-in-the-loop research pipeline called Democratic AI, in which reinforcement learning is used to design a social mechanism…