English
Related papers

Related papers: Inverse Constitutional AI: Compressing Preferences…

200 papers

This paper presents a novel teachable conversation interaction system that is capable of learning users preferences from cold start by gradually adapting to personal preferences. In particular, the TAI system is able to automatically…

Information Retrieval · Computer Science 2023-09-12 Deguang Kong , Abhay Jha , Lei Yun

This article unpacks the design choices behind longstanding and newly proposed computational frameworks aimed at finding common grounds across collective preferences and examines their potential future impacts, both technically and…

Computers and Society · Computer Science 2025-06-25 Manon Revel , Théophile Pénigaud

As AI agents become more autonomous, properly aligning their objectives with human preferences becomes increasingly important. We study how effectively an AI agent learns a human principal's preference in choice under risk via stated versus…

General Economics · Economics 2026-04-01 Keaton Ellis , Wanying Huang

Conversational AI (CAI) systems which encompass voice- and text-based assistants are on the rise and have been largely integrated into people's everyday lives. Despite their widespread adoption, users voice concerns regarding privacy,…

Human-Computer Interaction · Computer Science 2025-02-27 Anna Leschanowsky , Silas Rech , Birgit Popp , Tom Bäckström

Human decision makers increasingly delegate choices to AI agents, raising a natural question: does the AI implement the human principal's preferences or pursue its own? To study this question using revealed preference techniques, I…

Theoretical Economics · Economics 2026-03-31 Elchin Suleymanov

Hundreds of millions of people use artificial intelligence (AI) for writing assistance. Here, we evaluated how AI writing assistance distorts writer personas - their perceived beliefs, personality, and identity. In three large-scale…

Computation and Language · Computer Science 2026-04-27 Paul Röttger , Kobi Hackenburg , Hannah Rose Kirk , Christopher Summerfield

In this paper, we introduce a novel methodology to efficiently construct a corpus for question answering over structured data. For this, we introduce an intermediate representation that is based on the logical query plan in a database…

AI is anticipated to enhance human decision-making in high-stakes domains like aviation, but adoption is often hindered by challenges such as inappropriate reliance and poor alignment with users' decision-making. Recent research suggests…

Human-Computer Interaction · Computer Science 2024-09-23 Zelun Tony Zhang , Sebastian S. Feger , Lucas Dullenkopf , Rulu Liao , Lukas Süsslin , Yuanting Liu , Andreas Butz

In this paper, we propose Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems to avoid generic responses and model dialogue history better. In contrast to standard adversarial training algorithms, IAT…

Computation and Language · Computer Science 2021-06-01 Wangchunshu Zhou , Qifei Li , Chenle Li

Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is…

Machine Learning · Computer Science 2025-07-15 Hoang Anh Just , Ming Jin , Anit Sahu , Huy Phan , Ruoxi Jia

Practitioners commonly align large language models using pairwise preferences, i.e., given labels of the type response A is preferred to response B for a given input. Perhaps less commonly, methods have also been developed for binary…

Computation and Language · Computer Science 2024-04-24 Jing Xu , Andrew Lee , Sainbayar Sukhbaatar , Jason Weston

Conjoint experiments randomize multidimensional profiles, offering a powerful design for recovering structural preference parameters -- including marginal rates of substitution, willingness to pay, and the distribution of preferences across…

Methodology · Statistics 2026-05-26 Avidit Acharya , Jens Hainmueller , Yiqing Xu

Students in introductory physics courses often rely on ineffective strategies, focusing on final answers rather than understanding underlying principles. Integrating scientific argumentation into problem-solving fosters critical thinking…

Physics Education · Physics 2025-08-21 Winter Allen , Anand Shanker , N. Sanjay Rebello

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…

Artificial Intelligence · Computer Science 2026-05-12 Katarzyna Kobalczyk , Mihaela van der Schaar

Crowdsourced annotations of data play a substantial role in the development of Artificial Intelligence (AI). It is broadly recognised that annotations of text data can contain annotator bias, where systematic disagreement in annotations can…

Computation and Language · Computer Science 2024-10-22 Terne Sasha Thorn Jakobsen , Andreas Bjerre-Nielsen , Robert Böhm

Large language models (LLMs) are highly capable at a variety of tasks given the right prompt, but writing one is still a difficult and tedious process. In this work, we introduce ConstitutionalExperts, a method for learning a prompt…

Computation and Language · Computer Science 2024-03-11 Savvas Petridis , Ben Wedin , Ann Yuan , James Wexler , Nithum Thain

Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for…

An important use of machine learning is to learn what people value. What posts or photos should a user be shown? Which jobs or activities would a person find rewarding? In each case, observations of people's past choices can inform our…

Artificial Intelligence · Computer Science 2015-12-21 Owain Evans , Andreas Stuhlmueller , Noah D. Goodman

Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic…

Computation and Language · Computer Science 2025-06-16 Víctor Gallego

Social choice theory is the study of preference aggregation across a population, used both in mechanism design for human agents and in the democratic alignment of language models. In this study, we propose the representative social choice…

Machine Learning · Computer Science 2025-11-03 Tianyi Qiu