How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models.

Andrea Banino

Dharshan Kumaran Stephen M. Fleming Larisa Markeeva Joe Heyward Andrea Banino Mrinal Mathur Razvan Pascanu Simon Osindero Benedetto De Martino Petar Velickovic Viorica Patraucean How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models. 2025 July abs/2507.03120 CoRR https://doi.org/10.48550/arXiv.2507.03120 db/journals/corr/corr2507.html#abs-2507-03120 streams/journals/corr

Federico Barbero Andrea Banino Steven Kapturowski Dharshan Kumaran João Guilherme Madeira Araújo Oleksandr Vitvitskyi Razvan Pascanu Petar Velickovic Transformers need glasses! Information over-squashing in language tasks. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/b1d35561c4a4a0e0b6012b2af531e149-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#BarberoBKKAVPV24

Sahand Sharifzadeh Christos Kaplanis Shreya Pathak Dharshan Kumaran Anastasija Ilic Jovana Mitrovic Charles Blundell Andrea Banino Synth<sup>2</sup>: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings. 2024 abs/2403.07750 CoRR https://doi.org/10.48550/arXiv.2403.07750 db/journals/corr/corr2403.html#abs-2403-07750

Federico Barbero Andrea Banino Steven Kapturowski Dharshan Kumaran João G. M. Araújo Alex Vitvitskyi Razvan Pascanu Petar Velickovic Transformers need glasses! Information over-squashing in language tasks. 2024 abs/2406.04267 CoRR https://doi.org/10.48550/arXiv.2406.04267 db/journals/corr/corr2406.html#abs-2406-04267

Andrea Banino Adrià Puigdomènech Badia Jacob C. Walker Tim Scholtes Jovana Mitrovic Charles Blundell CoBERL: Contrastive BERT for Reinforcement Learning. 2022 ICLR https://openreview.net/forum?id=sRZ3GhmegS conf/iclr/2022 db/conf/iclr/iclr2022.html#BaninoBWSMB22 Anirudh Goyal Abram L. Friesen Andrea Banino Theophane Weber Nan Rosemary Ke Adrià Puigdomènech Badia Arthur Guez Mehdi Mirza Peter Conway Humphreys Ksenia Konyushkova Michal Valko Simon Osindero Timothy P. Lillicrap Nicolas Heess Charles Blundell Retrieval-Augmented Reinforcement Learning. 7740-7765 2022 ICML https://proceedings.mlr.press/v162/goyal22a.html conf/icml/2022 db/conf/icml/icml2022.html#GoyalFBWKBGMHKV22 Petar Velickovic Adrià Puigdomènech Badia David Budden Razvan Pascanu Andrea Banino Misha Dashevskiy Raia Hadsell Charles Blundell The CLRS Algorithmic Reasoning Benchmark. 22084-22102 2022 ICML https://proceedings.mlr.press/v162/velickovic22a.html conf/icml/2022 db/conf/icml/icml2022.html#VelickovicBBPBD22 Allison C. Tam Neil C. Rabinowitz Andrew K. Lampinen Nicholas A. Roy Stephanie C. Y. Chan DJ Strouse Jane Wang 0001 Andrea Banino Felix Hill Semantic Exploration from Language Abstractions and Pretrained Representations. 2022 conf/nips/2022 NeurIPS http://papers.nips.cc/paper_files/paper/2022/hash/a28e024ccd623ed113fb19683fa0910d-Abstract-Conference.html db/conf/nips/neurips2022.html#TamRLRCS0BH22

Anirudh Goyal Abram L. Friesen Andrea Banino Theophane Weber Nan Rosemary Ke Adrià Puigdomènech Badia Arthur Guez Mehdi Mirza Ksenia Konyushkova Michal Valko Simon Osindero Timothy P. Lillicrap Nicolas Heess Charles Blundell Retrieval-Augmented Reinforcement Learning. 2022 abs/2202.08417 CoRR https://arxiv.org/abs/2202.08417 db/journals/corr/corr2202.html#abs-2202-08417

Allison C. Tam Neil C. Rabinowitz Andrew K. Lampinen Nicholas A. Roy Stephanie C. Y. Chan DJ Strouse Jane X. Wang Andrea Banino Felix Hill Semantic Exploration from Language Abstractions and Pretrained Representations. 2022 abs/2204.05080 CoRR https://doi.org/10.48550/arXiv.2204.05080 db/journals/corr/corr2204.html#abs-2204-05080

Petar Velickovic Adrià Puigdomènech Badia David Budden Razvan Pascanu Andrea Banino Misha Dashevskiy Raia Hadsell Charles Blundell The CLRS Algorithmic Reasoning Benchmark. 2022 abs/2205.15659 CoRR https://doi.org/10.48550/arXiv.2205.15659 db/journals/corr/corr2205.html#abs-2205-15659

Augustine N. Mavor-Parker Andrea Banino Lewis D. Griffin Caswell Barry A Simple Approach for State-Action Abstraction using a Learned MDP Homomorphism. 2022 abs/2209.06356 CoRR https://doi.org/10.48550/arXiv.2209.06356 db/journals/corr/corr2209.html#abs-2209-06356

Andrew K. Lampinen Stephanie C. Y. Chan Andrea Banino Felix Hill Towards mental time travel: a hierarchical memory for reinforcement learning agents. 28182-28195 2021 NeurIPS https://proceedings.neurips.cc/paper/2021/hash/ed519dacc89b2bead3f453b0b05a4a8b-Abstract.html conf/nips/2021 db/conf/nips/neurips2021.html#LampinenCBH21

Andrew Kyle Lampinen Stephanie C. Y. Chan Andrea Banino Felix Hill Towards mental time travel: a hierarchical memory for reinforcement learning agents. 2021 abs/2105.14039 CoRR https://arxiv.org/abs/2105.14039 db/journals/corr/corr2105.html#abs-2105-14039

Andrea Banino Jan Balaguer Charles Blundell PonderNet: Learning to Ponder. 2021 abs/2107.05407 CoRR https://arxiv.org/abs/2107.05407 db/journals/corr/corr2107.html#abs-2107-05407

Andrea Banino Adrià Puigdomènech Badia Jacob C. Walker Tim Scholtes Jovana Mitrovic Charles Blundell CoBERL: Contrastive BERT for Reinforcement Learning. 2021 abs/2107.05431 CoRR https://arxiv.org/abs/2107.05431 db/journals/corr/corr2107.html#abs-2107-05431

Andrea Banino Adrià Puigdomènech Badia Raphael Köster Martin J. Chadwick Vinícius Flores Zambaldi Demis Hassabis Caswell Barry Matthew M. Botvinick Dharshan Kumaran Charles Blundell MEMO: A Deep Network for Flexible Combination of Episodic Memories. 2020 ICLR https://openreview.net/forum?id=rJxlc0EtDr conf/iclr/2020 db/conf/iclr/iclr2020.html#BaninoBKCZHBBKB20

Andrea Banino Adrià Puigdomènech Badia Raphael Köster Martin J. Chadwick Vinícius Flores Zambaldi Demis Hassabis Caswell Barry Matthew M. Botvinick Dharshan Kumaran Charles Blundell MEMO: A Deep Network for Flexible Combination of Episodic Memories. 2020 abs/2001.10913 CoRR https://arxiv.org/abs/2001.10913 db/journals/corr/corr2001.html#abs-2001-10913

Andrea Banino Caswell Barry Benigno Uria Charles Blundell Timothy P. Lillicrap Piotr Mirowski Alexander Pritzel Martin J. Chadwick Thomas Degris Joseph Modayil Greg Wayne Hubert Soyer Fabio Viola Brian Zhang 0001 Ross Goroshin Neil C. Rabinowitz Razvan Pascanu Charlie Beattie Stig Petersen Amir Sadik Stephen Gaffney Helen King Koray Kavukcuoglu Demis Hassabis Raia Hadsell Dharshan Kumaran Vector-based navigation using grid-like representations in artificial agents. 429-433 2018 557 Nat. 7705 https://doi.org/10.1038/s41586-018-0102-6 https://www.wikidata.org/entity/Q52990529 db/journals/nature/nature557.html#BaninoBUBLMPCDM18

Piotr Mirowski Razvan Pascanu Fabio Viola Hubert Soyer Andy Ballard Andrea Banino Misha Denil Ross Goroshin Laurent Sifre Koray Kavukcuoglu Dharshan Kumaran Raia Hadsell Learning to Navigate in Complex Environments. 2017 ICLR (Poster) https://openreview.net/forum?id=SJMGPrcle conf/iclr/2017 db/conf/iclr/iclr2017.html#MirowskiPVSBBDG17

Piotr Mirowski Razvan Pascanu Fabio Viola Hubert Soyer Andrew J. Ballard Andrea Banino Misha Denil Ross Goroshin Laurent Sifre Koray Kavukcuoglu Dharshan Kumaran Raia Hadsell Learning to Navigate in Complex Environments. 2016 abs/1611.03673 CoRR http://arxiv.org/abs/1611.03673 db/journals/corr/corr1611.html#MirowskiPVSBBDG16

João G. M. AraújoJoão Guilherme Madeira Araújo Adrià Puigdomènech Badia Jan Balaguer Andrew J. BallardAndy Ballard Federico Barbero Caswell Barry Charlie Beattie Charles Blundell Matt M. BotvinickMatthew M. Botvinick David Budden Martin J. Chadwick Stephanie C. Y. Chan Misha Dashevskiy Thomas Degris Misha Denil Stephen M. Fleming Abram L. Friesen Stephen Gaffney Ross Goroshin Anirudh Goyal Lewis D. Griffin Arthur Guez Raia Hadsell Demis Hassabis Nicolas Heess Joseph HeywardJoe Heyward Felix Hill Peter Conway Humphreys Anastasija Ilic Christos Kaplanis Steven Kapturowski Koray Kavukcuoglu Nan Rosemary Ke Helen King Ksenia Konyushkova Raphael KosterRaphael Köster Dharshan Kumaran Andrew K. LampinenAndrew Kyle Lampinen Timothy P. Lillicrap Larisa Markeeva Benedetto De Martino Mrinal Mathur Augustine N. Mavor-Parker Piotr Mirowski Mehdi Mirza Jovana Mitrovic Joseph Modayil Simon Osindero Razvan Pascanu Shreya Pathak Viorica Patraucean Stig Petersen Alexander Pritzel Neil C. Rabinowitz Nicholas A. Roy Amir Sadik Tim Scholtes Sahand Sharifzadeh Laurent Sifre Hubert Soyer DJ Strouse Allison C. Tam Benigno Uria Michal Valko Petar Velickovic Fabio Viola Alex VitvitskyiOleksandr Vitvitskyi Jacob C. Walker Jane X. WangJane Wang 0001 Greg Wayne Theophane Weber Vinícius Flores Zambaldi Brian Zhang 0001