Production and Perception in LLMs: A Token Probability Approach
The asymmetry between language production and perception has been well-documented in psycholinguistics. Whether large language models (LLMs) exhibit a functionally analogous distinction remains an open question, particularly given that LLMs rely on the same underlying mechanism (next-token prediction) for both input and output processing. In this exploratory study, we operationalize the production-perception distinction through direct token probability measurements rather than metalinguistic prompting. Using the base Llama-3.1-8B model, we generated poems under a production prompt and re-score
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) · 49%Furyton/awesome-language-model-analysis →
- PossiblePossibly related (embedding) · 46%sileod/llm-theory-of-mind →
- PossiblePossibly related (embedding) · 45%New Server Hopes to Break Through AI’s “Memory Wall” →
- LinkedLinked via arxiv author · 85%Anna Marklová →
“Production and Perception in LLMs: A Token Probability Approach”
- LinkedLinked via arxiv author · 85%Jiří Milička →
“Production and Perception in LLMs: A Token Probability Approach”
- LinkedLinked via arxiv author · 85%Martina Vokáčová →
“Production and Perception in LLMs: A Token Probability Approach”
- LinkedLinked via arxiv author · 85%Rudolf Rosa →
“Production and Perception in LLMs: A Token Probability Approach”
- FuzzySimilar title/name (fuzzy) · 84%tensorflow/probability →
“Fuzzy title match (0.92): “Production and Perception in LLMs: A Token Probability Appro” ≈ “tensorflow/probability””