Cover Image

Human Preferences in Large Language Model Latent Space: A Technical Analysis on the Reliability of Synthetic Data in Voting Outcome Prediction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ball, Sarah, Allmendinger, Simeon, Kreuter, Frauke, Kühl, Niklas
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reading Between the Tokens: Improving Preference Predictions through Mechanistic Forecasting
by: Ball, Sarah, et al.
Published: (2026)

Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models
by: Ball, Sarah, et al.
Published: (2024)

Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-Agent AI
by: Deck, Luca, et al.
Published: (2026)

CollaFuse: Navigating Limited Resources and Privacy in Collaborative Generative AI
by: Zipperling, Domenique, et al.
Published: (2024)

CollaFuse: Collaborative Diffusion Models
by: Allmendinger, Simeon, et al.
Published: (2024)

Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models
by: Ball, Sarah, et al.
Published: (2025)

Interactive Generation of Laparoscopic Videos with Diffusion Models
by: Iliash, Ivan, et al.
Published: (2024)

Where are the Humans? A Scoping Review of Fairness in Multi-agent AI Systems
by: Allmendinger, Simeon, et al.
Published: (2026)

On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
by: Ball, Sarah, et al.
Published: (2025)

Large Language Models Do Not Simulate Human Psychology
by: Schröder, Sarah, et al.
Published: (2025)

From Ground Truth to Measurement: A Statistical Framework for Human Labeling
by: Chew, Robert, et al.
Published: (2026)

Self-Boosting Large Language Models with Synthetic Preference Data
by: Dong, Qingxiu, et al.
Published: (2024)

Problem Solving Through Human-AI Preference-Based Cooperation
by: Dutta, Subhabrata, et al.
Published: (2024)

Configurable Safety Tuning of Language Models with Synthetic Preference Data
by: Gallego, Victor
Published: (2024)

Synthetic Data Generation for Phrase Break Prediction with Large Language Model
by: Lee, Hoyeon, et al.
Published: (2025)

Data Quality Challenges in Retrieval-Augmented Generation
by: Müller, Leopold, et al.
Published: (2025)

Leveraging Large Language Models and Survival Analysis for Early Prediction of Chemotherapy Outcomes
by: Shahid, Muhammad Faisal, et al.
Published: (2026)

Utilizing Data Fingerprints for Privacy-Preserving Algorithm Selection in Time Series Classification: Performance and Uncertainty Estimation on Unseen Datasets
by: Böcking, Lars, et al.
Published: (2024)

Human-AI Teaming Using Large Language Models: Boosting Brain-Computer Interfacing (BCI) and Brain Research
by: Kapitonova, Maryna, et al.
Published: (2024)

PromptPilot: Improving Human-AI Collaboration Through LLM-Enhanced Prompt Engineering
by: Gutheil, Niklas, et al.
Published: (2025)

Towards Avoiding the Data Mess: Industry Insights from Data Mesh Implementations
by: Bode, Jan, et al.
Published: (2023)

How Large Language Models are Designed to Hallucinate
by: Ackermann, Richard, et al.
Published: (2025)

Data-Centric Artificial Intelligence
by: Jakubik, Johannes, et al.
Published: (2022)

Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation
by: Chen, Qiyuan, et al.
Published: (2025)

Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiability
by: Orvalho, Pedro, et al.
Published: (2026)

Aligning Large Language Model Behavior with Human Citation Preferences
by: Ando, Kenichiro, et al.
Published: (2026)

Generating Reliable Synthetic Clinical Trial Data: The Role of Hyperparameter Optimization and Domain Constraints
by: Hahn, Waldemar, et al.
Published: (2025)

Towards Human-Understandable Multi-Dimensional Concept Discovery
by: Grobrügge, Arne, et al.
Published: (2025)

LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback
by: Mura, Raffaele, et al.
Published: (2025)

Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
by: Yuan, Chenchen, et al.
Published: (2026)

Uncovering Political Bias in Large Language Models using Parliamentary Voting Records
by: Chen, Jieying, et al.
Published: (2026)

Human Alignment of Large Language Models through Online Preference Optimisation
by: Calandriello, Daniele, et al.
Published: (2024)

Language Models Largely Exhibit Human-like Constituent Ordering Preferences
by: Tur, Ada Defne, et al.
Published: (2025)

Large Language Models Vote: Prompting for Rare Disease Identification
by: Oniani, David, et al.
Published: (2023)

Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models
by: Li, Hao, et al.
Published: (2024)

Integrating Machine Learning Ensembles and Large Language Models for Heart Disease Prediction Using Voting Fusion
by: Amin, Md. Tahsin, et al.
Published: (2026)

Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models
by: Liu, Yuliang, et al.
Published: (2026)

Complementarity in Human-AI Collaboration: Concept, Sources, and Evidence
by: Hemmer, Patrick, et al.
Published: (2024)

Can Large Language Models Capture Human Risk Preferences? A Cross-Cultural Study
by: Song, Bing, et al.
Published: (2025)

Learning Transferable Latent User Preferences for Human-Aligned Decision Making
by: Hyk, Alina, et al.
Published: (2026)