Masha Fedzechkina

According to our database, Masha Fedzechkina authored at least 13 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

LLMs are not (consistently) Bayesian: Quantifying internal (in)consistencies of LLMs' probabilistic beliefs.

Chacha Chen, Matthew Jörke, Adam Golinski, Masha Fedzechkina, Guillermo Sapiro, Sinead Williamson, Nicholas J. Foti

CoRR, May, 2026

What do your logits know? (The answer may surprise you!).

Masha Fedzechkina, Eleonora Gualdoni, Rita Ramos, Sinead Williamson

CoRR, April, 2026

ExpertLens: Activation steering features are highly interpretable.

Masha Fedzechkina, Eleonora Gualdoni, Sinead Williamson, Katherine Metcalf, Skyler Seto, Barry-John Theobald

Trans. Mach. Learn. Res., 2026

2025

Analyze the Neurons, not the Embeddings: Understanding When and Where LLM Representations Align with Humans.

Masha Fedzechkina, Eleonora Gualdoni, Sinead Williamson, Katherine Metcalf, Skyler Seto, Barry-John Theobald

CoRR, February, 2025

Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks.

Maureen de Seyssel, Jie Chi, Skyler Seto, Maartje ter Hoeve, Masha Fedzechkina, Natalie Schluter

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models.

Anirudh Sundar, Sinead Williamson, Katherine Metcalf, Barry-John Theobald, Skyler Seto, Masha Fedzechkina

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter.

Verena Blaschke, Masha Fedzechkina, Maartje ter Hoeve

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? It's Complicated.

Katherine Metcalf, Miguel Sarabia, Masha Fedzechkina, Barry-John Theobald

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Naturalistic Head Motion Generation from Speech.

Trisha Mittal, Zakaria Aldeneh, Masha Fedzechkina, Anurag Ranjan, Barry-John Theobald

Proceedings of the IEEE International Conference on Acoustics, 2023

On the Role of LIP Articulation in Visual Speech Perception.

Zakaria Aldeneh, Masha Fedzechkina, Skyler Seto, Katherine Metcalf, Miguel Sarabia, Nicholas Apostoloff, Barry-John Theobald

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Towards a Perceptual Model for Estimating the Quality of Visual Speech.

Zakaria Aldeneh, Masha Fedzechkina, Skyler Seto, Katherine Metcalf, Miguel Sarabia, Nicholas Apostoloff, Barry-John Theobald

CoRR, 2022

2020

Learners' bias to balance production effort against message uncertainty is independent of their native language.

Lucy Hall Hartley, Masha Fedzechkina

Proceedings of the 42th Annual Meeting of the Cognitive Science Society, 2020

Learners sacrifice robust communication as a result of a social bias.

Masha Fedzechkina, Gareth Roberts

Proceedings of the 42th Annual Meeting of the Cognitive Science Society, 2020