Katherine Metcalf

35 papers A* 6A 3B 1C 2Misc 2Journal 17Unranked 4

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Aligning LLMs by Predicting Preferences from User Writing Samples. ICML Stéphane Aroca-Ouellette, Natalie Mackraz, Barry-John Theobald, Katherine Metcalf
2025	J	`jnl`	Aligning LLMs by Predicting Preferences from User Writing Samples. CoRR Stéphane Aroca-Ouellette, Natalie Mackraz, Barry-John Theobald, Katherine Metcalf
2025	J	`jnl`	Analyze the Neurons, not the Embeddings: Understanding When and Where LLM Representations Align with Humans. CoRR Masha Fedzechkina, Eleonora Gualdoni, Sinead Williamson, Katherine Metcalf, Skyler Seto, Barry-John Theobald
2025	J	`jnl`	Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution. CoRR Falaah Arif Khan, Nivedha Sivakumar, Yinong Oliver Wang, Katherine Metcalf, Cezanne Camacho, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff
2025	A*	`conf`	Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs. ICML Yinong Oliver Wang, Nivedha Sivakumar, Falaah Arif Khan, Katherine Metcalf, Adam Golinski, Natalie Mackraz, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff
2025	—	`conf`	Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models. ACL (1) Anirudh Sundar, Sinead Williamson, Katherine Metcalf, Barry-John Theobald, Skyler Seto, Masha Fedzechkina
2025	J	`jnl`	Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models. CoRR Anirudh Sundar, Sinead Williamson, Katherine Metcalf, Barry-John Theobald, Skyler Seto, Masha Fedzechkina
2024	A*	`conf`	Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? It's Complicated. AAAI Katherine Metcalf, Miguel Sarabia, Masha Fedzechkina, Barry-John Theobald
2024	A*	`conf`	Hindsight PRIORs for Reward Learning from Human Preferences. ICLR Mudit Verma, Katherine Metcalf
2024	J	`jnl`	Hindsight PRIORs for Reward Learning from Human Preferences. CoRR Mudit Verma, Katherine Metcalf
2024	—	`conf`	On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization. EMNLP (Findings) Yong Lin, Skyler Seto, Maartje ter Hoeve, Katherine Metcalf, Barry-John Theobald, Xuan Wang, Yizhe Zhang, Chen Huang, Tong Zhang
2024	J	`jnl`	On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization. CoRR Yong Lin, Skyler Seto, Maartje ter Hoeve, Katherine Metcalf, Barry-John Theobald, Xuan Wang, Yizhe Zhang, Chen Huang, Tong Zhang
2024	J	`jnl`	On the Way to LLM Personalization: Learning to Remember User Conversations. CoRR Lucie Charlotte Magister, Katherine Metcalf, Yizhe Zhang, Maartje ter Hoeve
2024	J	`jnl`	PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectories. CoRR Stephane Aroca-Ouellette, Natalie Mackraz, Barry-John Theobald, Katherine Metcalf
2024	J	`jnl`	Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards. CoRR Katherine Metcalf, Miguel Sarabia, Natalie Mackraz, Barry-John Theobald
2024	A*	`conf`	Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models. ICML Xavier Suau, Pieter Delobelle, Katherine Metcalf, Armand Joulin, Nicholas Apostoloff, Luca Zappella, Pau Rodríguez
2024	J	`jnl`	Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models. CoRR Xavier Suau, Pieter Delobelle, Katherine Metcalf, Armand Joulin, Nicholas Apostoloff, Luca Zappella, Pau Rodríguez
2023	J	`jnl`	Large Language Models as Generalizable Policies for Embodied Tasks. CoRR Andrew Szot, Max Schwarzer, Harsh Agrawal, Bogdan Mazoure, Walter Talbott, Katherine Metcalf, Natalie Mackraz, R. Devon Hjelm, Alexander Toshev
2023	Misc	`conf`	On the Role of LIP Articulation in Visual Speech Perception. ICASSP Zakaria Aldeneh, Masha Fedzechkina, Skyler Seto, Katherine Metcalf, Miguel Sarabia, Nicholas Apostoloff, Barry-John Theobald
2023	Misc	`conf`	Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards. CoRL Katherine Metcalf, Miguel Sarabia, Natalie Mackraz, Barry-John Theobald
2022	J	`jnl`	FedEmbed: Personalized Private Federated Learning. CoRR Andrew Silva, Katherine Metcalf, Nicholas Apostoloff, Barry-John Theobald
2022	J	`jnl`	Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning. CoRR Katherine Metcalf, Miguel Sarabia, Barry-John Theobald
2022	J	`jnl`	Symbol Guided Hindsight Priors for Reward Learning from Human Preferences. CoRR Mudit Verma, Katherine Metcalf
2022	J	`jnl`	Towards a Perceptual Model for Estimating the Quality of Visual Speech. CoRR Zakaria Aldeneh, Masha Fedzechkina, Skyler Seto, Katherine Metcalf, Miguel Sarabia, Nicholas Apostoloff, Barry-John Theobald
2019	A	`conf`	Mirroring to Build Trust in Digital Assistants. INTERSPEECH Katherine Metcalf, Barry-John Theobald, Garrett Weinberg, Robert Lee, Ing-Marie Jonsson, Russ Webb, Nicholas Apostoloff
2019	J	`jnl`	Mirroring to Build Trust in Digital Assistants. CoRR Katherine Metcalf, Barry-John Theobald, Garrett Weinberg, Robert Lee, Ing-Marie Jonsson, Russ Webb, Nicholas Apostoloff
2019	A*	`conf`	Unsupervised Hierarchical Temporal Abstraction by Simultaneously Learning Expectations and Representations. IJCAI Katherine Metcalf, David Leake
2018	C	`conf`	Embedded Word Representations for Rich Indexing: A Case Study for Medical Records. ICCBR Katherine Metcalf, David Leake
2018	A	`conf`	Learning Sharing Behaviors with Arbitrary Numbers of Agents. AAMAS Katherine Metcalf, Barry-John Theobald, Nicholas Apostoloff
2018	J	`jnl`	Learning Sharing Behaviors with Arbitrary Numbers of Agents. CoRR Katherine Metcalf, Barry-John Theobald, Nicholas Apostoloff
2017	B	`conf`	Modelling Unsupervised Event Segmentation: Learning Event Boundaries from Prediction Errors. CogSci Katherine Metcalf, David Leake
2016	A	`conf`	A Computational Method for Extracting, Representing, and Predicting Social Closeness. ECAI Katherine Metcalf, David B. Leake
2015	—	`conf`	Investigating Methods and Representations for Reasoning About Social Context and Relative Social Power. CONTEXT Katherine Metcalf, David Leake
2013	—	`conf`	Automated Methods for Extracting and Expanding Lists in Regulatory Text. DoCoPe@JURIX Alan Buabuchachart, Nina Charness, Katherine Metcalf, Leora Morgenstern
2013	C	`conf`	Classification of Regulatory Paragraphs by Discourse Structure, Reference Structure, and Regulation Type. JURIX Alan Buabuchachart, Katherine Metcalf, Nina Charness, Leora Morgenstern