Copertina

Growth First, Care Second? Tracing the Landscape of LLM Value Preferences in Everyday Dilemmas

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Zhiyi, Choi, Eun Cheol, Luo, Yingjia, Wang, Xinyi, Xiao, Yulei, Yang, Aizi, Luceri, Luca
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computers and Society Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Synthetic Politics: Prevalence, Spreaders, and Emotional Reception of AI-Generated Political Images on X
di: Chen, Zhiyi, et al.
Pubblicazione: (2025)

FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs
di: Choi, Eun Cheol, et al.
Pubblicazione: (2024)

Limited Effectiveness of LLM-based Data Augmentation for COVID-19 Misinformation Stance Detection
di: Choi, Eun Cheol, et al.
Pubblicazione: (2025)

The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks
di: Møller, Anders Giovanni, et al.
Pubblicazione: (2023)

Normative Evaluation of Large Language Models with Everyday Moral Dilemmas
di: Sachdeva, Pratik S., et al.
Pubblicazione: (2025)

Information Pathways in Online Science Communication: The Role of Platform Actors and News Media
di: Efstratiou, Alexandros, et al.
Pubblicazione: (2026)

Coordinated Activity Modulates the Behavior and Emotions of Organic Users: A Case Study on Tweets about the Gaza Conflict
di: Dey, Priyanka, et al.
Pubblicazione: (2024)

The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas
di: Wu, Ya, et al.
Pubblicazione: (2025)

Value Drifts: Tracing Value Alignment During LLM Post-Training
di: Bhatia, Mehar, et al.
Pubblicazione: (2025)

Harm in AI-Driven Societies: An Audit of Toxicity Adoption on Chirper.ai
di: Coppolillo, Erica, et al.
Pubblicazione: (2026)

Uncovering Coordinated Cross-Platform Information Operations Threatening the Integrity of the 2024 U.S. Presidential Election Online Discussion
di: Minici, Marco, et al.
Pubblicazione: (2024)

Susceptibility to Unreliable Information Sources: Swift Adoption with Minimal Exposure
di: Ye, Jinyi, et al.
Pubblicazione: (2023)

Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph
di: Tang, Zhenheng, et al.
Pubblicazione: (2026)

Fair Knowledge Tracing in Second Language Acquisition
di: Tang, Weitao, et al.
Pubblicazione: (2024)

Mapping Election Toxicity on Social Media across Issue, Ideology, and Psychosocial Dimensions
di: Cao, Lei, et al.
Pubblicazione: (2026)

Between Filters and Feeds: Investigating Douyin and WeChat's Influence on Chinese Adolescent Body Image
di: Lan, Jianfeng, et al.
Pubblicazione: (2025)

Personal Care Utility (PCU): Building the Health Infrastructure for Everyday Insight and Guidance
di: Abbasian, Mahyar, et al.
Pubblicazione: (2025)

Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
di: Chiu, Yu Ying, et al.
Pubblicazione: (2025)

Simulating Ethics: Using LLM Debate Panels to Model Deliberation on Medical Dilemmas
di: Zohny, Hazem
Pubblicazione: (2025)

Bridging the Narrative Divide: Cross-Platform Discourse Networks in Fragmented Ecosystems
di: Gerard, Patrick, et al.
Pubblicazione: (2025)

Online search is more likely to lead students to validate true news than to refute false ones
di: Bouleimen, Azza, et al.
Pubblicazione: (2023)

Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?
di: Fontana, Nicoló, et al.
Pubblicazione: (2024)

Safe Spaces or Toxic Places? Content Moderation and Social Dynamics of Online Eating Disorder Communities
di: Lerman, Kristina, et al.
Pubblicazione: (2024)

Implicit Humanization in Everyday LLM Moral Judgments
di: Ayad, Hoda, et al.
Pubblicazione: (2026)

The Traffickers' Pitch: Detecting Deceptive Recruitment in Online Job Boards
di: Zhou, Siyi, et al.
Pubblicazione: (2026)

When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas
di: Backmann, Steffen, et al.
Pubblicazione: (2025)

Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences
di: Ashkinaze, Joshua, et al.
Pubblicazione: (2025)

From Descriptive to Prescriptive: Uncover the Social Value Alignment of LLM-based Agents
di: Qu, Jinxian, et al.
Pubblicazione: (2026)

The Dilemma Between Euphoria and Freedom in Recommendation Algorithms
di: Brusseau, James
Pubblicazione: (2025)

Prioritization First, Principles Second: An Adaptive Interpretation of Helpful, Honest, and Harmless Principles
di: Huang, Yue, et al.
Pubblicazione: (2025)

Modeling Decision-Making with Will for Cooperation in Social Dilemmas
di: Huang, Yizhe, et al.
Pubblicazione: (2026)

ShaRP: Explaining Rankings and Preferences with Shapley Values
di: Pliatsika, Venetia, et al.
Pubblicazione: (2024)

The GPT Dilemma: Foundation Models and the Shadow of Dual-Use
di: Hickey, Alan
Pubblicazione: (2024)

Routed Closure: Rethinking Value Capture in Decentralized Ecosystems
di: Luo, Xubin
Pubblicazione: (2026)

Understanding the Landscape of Leveraging IoT for Sustainable Growth in Saudi Arabia
di: Alshehri, Manal, et al.
Pubblicazione: (2024)

Mapping the Climate Change Landscape on TikTok
di: Galdeman, Alessia, et al.
Pubblicazione: (2025)

"More Than Words": Linking Music Preferences and Moral Values Through Lyrics
di: Preniqi, Vjosa, et al.
Pubblicazione: (2022)

Labeled Datasets for Research on Information Operations
di: Seckin, Ozgur Can, et al.
Pubblicazione: (2024)

Principles and Reasons Behind Automated Vehicle Decisions in Ethically Ambiguous Everyday Scenarios
di: Suryana, Lucas Elbert, et al.
Pubblicazione: (2025)

RLHF May Not Reflect Genuine Preferences
di: Ghafouri, Bijean, et al.
Pubblicazione: (2026)