Andreas Opedal
@andreasopedal.bsky.social
PhD student at ETH Zurich & MPI-IS in NLP & ML
Language, Reasoning, and Cognition
https://opedal.github.io
Language, Reasoning, and Cognition
https://opedal.github.io
Reposted by Andreas Opedal
Andreas Opedal, Yanick Zengaffinen, Haruki Shirakami, Clemente Pasti, Mrinmaya Sachan, Abulhair Saparov, Ryan Cotterell, Bernhard Sch\"olkopf
Are Language Models Efficient Reasoners? A Perspective from Logic Programming
https://arxiv.org/abs/2510.25626
Are Language Models Efficient Reasoners? A Perspective from Logic Programming
https://arxiv.org/abs/2510.25626
October 30, 2025 at 5:25 AM
Andreas Opedal, Yanick Zengaffinen, Haruki Shirakami, Clemente Pasti, Mrinmaya Sachan, Abulhair Saparov, Ryan Cotterell, Bernhard Sch\"olkopf
Are Language Models Efficient Reasoners? A Perspective from Logic Programming
https://arxiv.org/abs/2510.25626
Are Language Models Efficient Reasoners? A Perspective from Logic Programming
https://arxiv.org/abs/2510.25626
Reposted by Andreas Opedal
Francesco Ignazio Re, Andreas Opedal, Glib Manaiev, Mario Giulianelli, Ryan Cotterell: A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading Behavior https://arxiv.org/abs/2506.19999 https://arxiv.org/pdf/2506.19999 https://arxiv.org/html/2506.19999
June 26, 2025 at 6:32 AM
Francesco Ignazio Re, Andreas Opedal, Glib Manaiev, Mario Giulianelli, Ryan Cotterell: A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading Behavior https://arxiv.org/abs/2506.19999 https://arxiv.org/pdf/2506.19999 https://arxiv.org/html/2506.19999
New #ICLR2025 paper 📣📣
We argue that to properly evaluate a model’s reasoning ability, it must be tested on problems that are harder than the ones it has already seen. Enter MathGAP, an evaluation framework for math word problems with arbitrarily complex proofs🧵
arxiv.org/abs/2410.13502
We argue that to properly evaluate a model’s reasoning ability, it must be tested on problems that are harder than the ones it has already seen. Enter MathGAP, an evaluation framework for math word problems with arbitrarily complex proofs🧵
arxiv.org/abs/2410.13502
March 14, 2025 at 4:14 PM
New #ICLR2025 paper 📣📣
We argue that to properly evaluate a model’s reasoning ability, it must be tested on problems that are harder than the ones it has already seen. Enter MathGAP, an evaluation framework for math word problems with arbitrarily complex proofs🧵
arxiv.org/abs/2410.13502
We argue that to properly evaluate a model’s reasoning ability, it must be tested on problems that are harder than the ones it has already seen. Enter MathGAP, an evaluation framework for math word problems with arbitrarily complex proofs🧵
arxiv.org/abs/2410.13502
Reposted by Andreas Opedal
Andreas Opedal, Eleanor Chodroff, Ryan Cotterell, Ethan Gotlieb Wilcox
On the Role of Context in Reading Time Prediction
https://arxiv.org/abs/2409.08160
On the Role of Context in Reading Time Prediction
https://arxiv.org/abs/2409.08160
October 11, 2024 at 3:01 AM
Andreas Opedal, Eleanor Chodroff, Ryan Cotterell, Ethan Gotlieb Wilcox
On the Role of Context in Reading Time Prediction
https://arxiv.org/abs/2409.08160
On the Role of Context in Reading Time Prediction
https://arxiv.org/abs/2409.08160
Reposted by Andreas Opedal
Mario Giulianelli, Andreas Opedal, Ryan Cotterell
Generalized Measures of Anticipation and Responsivity in Online Language Processing
https://arxiv.org/abs/2409.10728
Generalized Measures of Anticipation and Responsivity in Online Language Processing
https://arxiv.org/abs/2409.10728
October 16, 2024 at 3:01 AM
Mario Giulianelli, Andreas Opedal, Ryan Cotterell
Generalized Measures of Anticipation and Responsivity in Online Language Processing
https://arxiv.org/abs/2409.10728
Generalized Measures of Anticipation and Responsivity in Online Language Processing
https://arxiv.org/abs/2409.10728