Imagen de Portada

Maximizing Signal in Human-Model Preference Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kraus, Kelsey, Kroll, Margaret
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Methodology
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Optimizing the role of human evaluation in LLM-based spoken document summarization systems
por: Kroll, Margaret, et al.
Publicado: (2024)

How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment
por: Jung, Julie, et al.
Publicado: (2025)

Optimizing Language Models for Human Preferences is a Causal Inference Problem
por: Lin, Victoria, et al.
Publicado: (2024)

MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment
por: Wang, Tianze, et al.
Publicado: (2025)

Debiasing Watermarks for Large Language Models via Maximal Coupling
por: Xie, Yangxinyu, et al.
Publicado: (2024)

Human-AI Co-design for Clinical Prediction Models
por: Feng, Jean, et al.
Publicado: (2026)

Discovering influential text using convolutional neural networks
por: Ayers, Megan, et al.
Publicado: (2024)

Syntax-Guided Diffusion Language Models with User-Integrated Personalization
por: Zhang, Ruqian, et al.
Publicado: (2025)

A New Semisupervised Technique for Polarity Analysis using Masked Language Models
por: Watanabe, Kohei
Publicado: (2026)

Distributed Asymmetric Allocation: A Topic Model for Large Imbalanced Corpora in Social Sciences
por: Watanabe, Kohei
Publicado: (2025)

An Embedded Diachronic Sense Change Model with a Case Study from Ancient Greek
por: Zafar, Schyan, et al.
Publicado: (2023)

Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication
por: Eckman, Stephanie, et al.
Publicado: (2025)

Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts
por: Li, Xiang, et al.
Publicado: (2025)

Segmenting Human-LLM Co-authored Text via Change Point Detection
por: Li, Mengchu, et al.
Publicado: (2026)

Robust Detection of Watermarks for Large Language Models Under Human Edits
por: Li, Xiang, et al.
Publicado: (2024)

Systematic Evaluation of Uncertainty Estimation Methods in Large Language Models
por: Hobelsberger, Christian, et al.
Publicado: (2025)

Improving Probabilistic Models in Text Classification via Active Learning
por: Bosley, Mitchell, et al.
Publicado: (2022)

(Mis)Fitting: A Survey of Scaling Laws
por: Li, Margaret, et al.
Publicado: (2025)

A chart review process aided by natural language processing and multi-wave adaptive sampling to expedite validation of code-based algorithms for large database studies
por: Wang, Shirley V, et al.
Publicado: (2025)

Geological Inference from Textual Data using Word Embeddings
por: Linphrachaya, Nanmanas, et al.
Publicado: (2025)

Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis
por: Ledberg, Anders, et al.
Publicado: (2025)

Automated scoring of the Ambiguous Intentions Hostility Questionnaire using fine-tuned large language models
por: Lyu, Y., et al.
Publicado: (2025)

A Position Paper on the Automatic Generation of Machine Learning Leaderboards
por: Timmer, Roelien C, et al.
Publicado: (2025)

Differential contributions of machine learning and statistical analysis to language and cognitive sciences
por: Sun, Kun, et al.
Publicado: (2024)

Exploring Intra and Inter-language Consistency in Embeddings with ICA
por: Li, Rongzhi, et al.
Publicado: (2024)

Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judges
por: Li, Yanran
Publicado: (2026)

Quantifying and Mitigating Socially Desirable Responding in LLMs: A Desirability-Matched Graded Forced-Choice Psychometric Study
por: Okada, Kensuke, et al.
Publicado: (2026)

Isolated Causal Effects of Natural Language
por: Lin, Victoria, et al.
Publicado: (2024)

A Finite-Calibration Regime Map for LLM Judge Panels
por: Zhu, Bin, et al.
Publicado: (2026)

Omitted Variable Bias in Language Models Under Distribution Shift
por: Lin, Victoria, et al.
Publicado: (2026)

CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models
por: Tu, Ruibo, et al.
Publicado: (2024)

Annotation Sensitivity: Training Data Collection Methods Affect Model Performance
por: Kern, Christoph, et al.
Publicado: (2023)

Using Large Language Models to Suggest Informative Prior Distributions in Bayesian Statistics
por: Riegler, Michael A., et al.
Publicado: (2025)

Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models
por: Zhang, Yuzhe, et al.
Publicado: (2024)

TWIN-GPT: Digital Twins for Clinical Trials via Large Language Model
por: Wang, Yue, et al.
Publicado: (2024)

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

Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models
por: Egami, Naoki, et al.
Publicado: (2023)

Documents Are People and Words Are Items: A Psychometric Approach to Textual Data with Contextual Embeddings
por: Chen, Jinsong
Publicado: (2025)

Constructing the Truth: Text Mining and Linguistic Networks in Public Hearings of Case 03 of the Special Jurisdiction for Peace (JEP)
por: Sosa, Juan, et al.
Publicado: (2025)

Leveraging text data for causal inference using electronic health records
por: Mozer, Reagan, et al.
Publicado: (2023)