Energy from energy-based transformers predicts reading times better than surprisal alone and captures subject/object relative clause asymmetries while subsuming attention-entropy effects.
Psychometric Predictive Power of Large Language Models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Apparent psychological profiles of LLMs are largely measurement artifacts driven by directional response bias rather than actual traits.
Surprisal minimization over goal-directed alternatives generated by language models provides the strongest account of production choices in open-ended dialogue compared to uniform information density or length-based costs.
Dutch LLMs display coherence illusions tracked by surprisal, with attention entropy identifying affected heads and a new energy metric quantifying discourse coherence.
citing papers explorer
-
Energy-Based Transformers as Predictors of Reading Difficulty
Energy from energy-based transformers predicts reading times better than surprisal alone and captures subject/object relative clause asymmetries while subsuming attention-entropy effects.
-
Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact
Apparent psychological profiles of LLMs are largely measurement artifacts driven by directional response bias rather than actual traits.
-
Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue
Surprisal minimization over goal-directed alternatives generated by language models provides the strongest account of production choices in open-ended dialogue compared to uniform information density or length-based costs.
-
When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs
Dutch LLMs display coherence illusions tracked by surprisal, with attention entropy identifying affected heads and a new energy metric quantifying discourse coherence.