Neural-network agents trained in social environments learn hybrid navigation strategies that combine individual landmark use with social following, with strategy shifts driven by the ratio of skilled to unskilled social agents.
and Kaiser, Daniel, year = 2019, month = apr
5 Pith papers cite this work, alongside 483 external citations. Polarity classification is still indexing.
5
Pith papers citing it
483
external citations · OpenAlex
representative citing papers
CDS-trained BabyLMs show earlier and more appropriate production in a new frame-completion task while FineWeb-edu models lead on comprehension benchmarks, indicating current tests underestimate CDS benefits.
Varying the number of simultaneous parses in RNNGs increases predicted garden-path effects but does not fully reconcile LM surprisal with human reading times.
RSA on 7T fMRI during natural scene viewing identifies ventromedial and lateral occipitotemporal representational routes for scene context versus animate content, with differential alignment to vision and language models.
The paper reviews Transformer architecture, emergent LLM capabilities resembling cognition, explainable AI methods, and argues against both anthropomorphism and overly reductive views of LLM behavior as mere memorization.
citing papers explorer
-
Social-spatial dependencies for learning visual navigation
Neural-network agents trained in social environments learn hybrid navigation strategies that combine individual landmark use with social following, with strategy shifts driven by the ratio of skilled to unskilled social agents.
-
Child-directed speech facilitates production, not comprehension, in BabyLMs
CDS-trained BabyLMs show earlier and more appropriate production in a new frame-completion task while FineWeb-edu models lead on comprehension benchmarks, indicating current tests underestimate CDS benefits.
-
Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis
Varying the number of simultaneous parses in RNNGs increases predicted garden-path effects but does not fully reconcile LM surprisal with human reading times.
-
Shared representations in brains and models reveal a two-route cortical organization during scene perception
RSA on 7T fMRI during natural scene viewing identifies ventromedial and lateral occipitotemporal representational routes for scene context versus animate content, with differential alignment to vision and language models.
-
Understanding Large Language Models
The paper reviews Transformer architecture, emergent LLM capabilities resembling cognition, explainable AI methods, and argues against both anthropomorphism and overly reductive views of LLM behavior as mere memorization.