Natalie Mackraz

5 papers · 2023–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) ❓ The Questioner

Venues

ICML (2) CoRL (1) EMNLP (1) ICLR (1)

Top co-authors

Barry-John Theobald (4) Katherine Metcalf (3) Luca Zappella (2) Nicholas Apostoloff (2) Nivedha Sivakumar (2) Miguel Sarabia (1) Yinong Oliver Wang (1) Walter Talbott (1) Adam Golinski (1) Max Schwarzer (1)

Research topics

Artificial Intelligence (5) Core AI (4) Learning Paradigms (2) Machine Learning (1) Natural Language Processing (1) Reinforcement Learning (1) Learning Types (1) Methods (1) Resources & Methods (1)

Keywords

large language model (2) sample efficiency (1) few-shot learning (1) self-supervised learning (1) policy learning (1) visual navigation (1) coreference resolution (1) embodied ai (1) iterative refinement (1) model uncertainty (1) reward function (1) preference-based reinforcement learning (1) debiasing strategy (1) bias transfer (1) prompt adaptation (1) dynamics encoding (1) writing sample (1) verification (1) llms (1) generation (1)

Papers

Aligning LLMs by Predicting Preferences from User Writing Samples ICML 2025 Bias after Prompting: Persistent Discrimination in Large Language Models EMNLP 2025 Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs ICML 2025 Large Language Models as Generalizable Policies for Embodied Tasks ICLR 2024 Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards CoRL 2023