surprisal is Not a Theory
Surprisal Theory is often characterized as a computational-level explanation per (Marr, 1982). We argue in this work that, even though a computational level narrative has been used to support "representation-agnostic research" within computational psycholinguistics, the movement toward black box systems embodied by large language models (LLMs) does not exempt modelers using the surprisal metric from the representational decisions required by computational-level characterizations. In fact, we argue that the uncritical use of LLM-surprisal obfuscates the representational and algorithmic-level co
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 62%Understanding large language models demands distinguishing human projection from machine cognition - Nature →
- PossiblePossibly related (embedding) · 53%WAIC 2026 Deep Dive: Large Language Models Retreat Behind the Scenes as AI Agents and Embodied Intelligence Take Center Stage - finance.biggo.com →
- PossiblePossibly related (embedding) · 52%Do Large Language Models Think Like Us? - Psychology Today →
- PossiblePossibly related (embedding) · 52%Knowledge Distillation of Black-Box Large Language Models →
- PossiblePossibly related (embedding) · 49%Knowledge Distillation of Black-Box Large Language Models (2024) →
- LinkedLinked via arxiv author · 85%Andrés Buxó-Lugo →
“surprisal is Not a Theory”
- LinkedLinked via arxiv author · 85%Aniello De Santo →
“surprisal is Not a Theory”
- LinkedLinked via arxiv author · 85%Morgan Grobol →
“surprisal is Not a Theory”