9 citations · 33 across the 12 of their papers we have counts for
12 papers
Independent-Component-Based Encoding Models of Brain Activity During Story Comprehension
Kamya Hari, Taha Binhuraib, Jin Li +2
Encoding models provide a powerful framework for linking continuous stimulus features to neural activity; however, traditional voxelwise approaches are limited by measurement noise…
What does it mean to understand language?
Colton Casto, Anna Ivanova, Evelina Fedorenko +1
Language understanding entails not just extracting the surface-level meaning of the linguistic input, but constructing rich mental models of the situation it describes. Here we pro…
How Do LLMs Use Their Depth?
Akshat Gupta, Jay Yeung, Gopala Anumanchipalli +1
Growing evidence suggests that large language models do not use their depth uniformly, yet we still lack a fine-grained understanding of their layer-wise prediction dynamics. In th…
LITcoder: A General-Purpose Library for Building and Comparing Encoding Models
Taha Binhuraib, Ruimin Gao, Anna A. Ivanova
We introduce LITcoder, an open-source library for building and benchmarking neural encoding models. Designed as a flexible backend, LITcoder provides standardized tools for alignin…
Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience
Zhonghao He, Jascha Achterberg, Katie Collins +13
As deep learning systems are scaled up to many billions of parameters, relating their internal structure to external behaviors becomes very challenging. Although daunting, this pro…
Log Probabilities Are a Reliable Estimate of Semantic Plausibility in Base and Instruction-Tuned Language Models
Carina Kauf, Emmanuele Chersoni, Alessandro Lenci +2
Semantic plausibility (e.g. knowing that "the actor won the award" is more likely than "the actor won the battle") serves as an effective proxy for general world knowledge. Languag…
A Better Way to Do Masked Language Model Scoring
Carina Kauf, Anna Ivanova
Estimating the log-likelihood of a given sentence under an autoregressive language model is straightforward: one can simply apply the chain rule and sum the log-likelihood values f…
Program Comprehension Does Not Primarily Rely On the Language Centers of the Human Brain
Shashank Srikant, Anna A. Ivanova, Yotaro Sueoka +5
Our goal is to identify brain regions involved in comprehending computer programs. We use functional magnetic resonance imaging (fMRI) to investigate two candidate systems of brain…
Event knowledge in large language models: the gap between the impossible and the unlikely
Carina Kauf, Anna A. Ivanova, Giulia Rambelli +5
Word co-occurrence patterns in language corpora contain a surprising amount of conceptual knowledge. Large language models (LLMs), trained to predict words in context, leverage the…
Beyond linear regression: mapping models in cognitive neuroscience should align with research goals
Anna A. Ivanova, Martin Schrimpf, Stefano Anzellotti +3
Many cognitive neuroscience studies use large feature sets to predict and interpret brain activity patterns. Feature sets take many forms, from human stimulus annotations to repres…
Probing artificial neural networks: insights from neuroscience
Anna A. Ivanova, John Hewitt, Noga Zaslavsky
A major challenge in both neuroscience and machine learning is the development of useful tools for understanding complex information processing systems. One such tool is probes, i.…
Does the brain represent words? An evaluation of brain decoding studies of language understanding
Jon Gauthier, Anna Ivanova
Language decoding studies have identified word representations which can be used to predict brain activity in response to novel words and sentences (Anderson et al., 2016; Pereira…