paper-with-me

Papers

Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback

2024-04-16 · Vincent Conitzer, Rachel Freedman, Jobst Heitzig, Wesley H. Holliday, Bob M. Jacobs, Nathan Lambert, Milan Mossé, Eric Pacuit, Stuart Russell, Hailey Schoelkopf, Emanuel Tewolde, William S. Zwicker

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans' expressed preferences over multiple outputs. Another approach is constitutional AI, in which the input from humans is a list of high-level principles. But how do we deal with potentially diverging input from humans? How can we aggregate the input into consistent data about "collective" preferences or otherwise use it to make collective choices about model behavior? In this paper, we argue that the field of social choice is well positioned to address these questions, and we discuss ways forward for this agenda, drawing on discussions in a recent workshop on Social Choice for AI Ethics and Safety held in Berkeley, CA, USA in December 2023.

📄 PDF Abstract BibTeX arXiv:2404.10271

Code (0)

등록된 구현이 없습니다.

Tasks

Ethics

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

AI Alignment From Social Choice Perspectives

2026-06-19 · Daniel Halpern, Evi Micha, Ariel D. Procaccia, Benjamin Schiffer 외 arxiv

Alignment from human feedback uses human judgments about model outputs to steer the behavior of language models after pretraining. When those judgments reflect conflicting views of desirable behavior, the learned objecti…

Representative Social Choice: From Learning Theory to AI Alignment

2024-10-31 · Tianyi Qiu

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 representa…

Decision MakingLanguage ModelingLanguage ModellingLearning Theory

AI of the People, by the People, for the People: A Social Choice Approach to Collective Control of Artificial Intelligence

2026-04-14 · Paul Anton Bachmann, Niclas Boehmer, Lukas Daniel Klausner, Martin Lackner arxiv

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 con…

AI Alignment and Social Choice: Fundamental Limitations and Policy Implications

2023-10-24 · Abhilash Mishra

Aligning AI agents to human intentions and values is a key bottleneck in building safe and deployable AI applications. But whose values should AI agents be aligned with? Reinforcement learning with human feedback (RLHF) …

Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment

2026-02-03 · Zhiyu An, Wan Du arxiv

Social choice has become a foundational component of modern machine learning systems. From auctions and resource allocation to the alignment of large generative models, machine learning pipelines increasingly aggregate h…