Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

subjective human preferences

Subjective human preferences are the individualized tastes, ethical values, stylistic inclinations, and qualitative judgments that guide people when evaluating choices, behaviors, or content. Unlike objective criteria such as factual accuracy or logical validity, subjective preferences do not have a universally verifiable ground truth, as they inherently vary across different cultural, demographic, and personal perspectives. In computational systems and machine learning, capturing subjective human preferences involves learning from human feedback on nuanced topics where multiple valid interpretations or competing values exist, rather than optimizing for a single, deterministic standard of correctness.

1 item

The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values

The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values

Hannah Kirk, Andrew M. Bean, Bertie Vidgen, Paul Röttger, Scott Hale

OrganizationsBocconi UniversityMeedanUniversity of Oxford

Why you should read this

Systematizes the evolution of human feedback learning across 95 studies to identify critical conceptual and practical challenges in aligning language models with subjective preferences and values.

Human feedback is increasingly used to steer the behaviours of Large Language Models (LLMs). However, it is unclear how to collect and incorporate feedback in a way that is efficient, effective and unbiased, especially for highly subjective human preferences and values. In this paper, we survey existing approaches for learning from human feedback, drawing on 95 papers primarily from the ACL and arXiv repositories. First, we summarise the past, pre-LLM trends for integrating human feedback into language models. Second, we give an overview of present techniques and practices, as well as the motivations for using feedback; conceptual frameworks for defining values and preferences; and how feedback is collected and from whom. Finally, we encourage a better future of feedback learning in LLMs by raising five unresolved conceptual and practical challenges.

Added

2026-09-26