Mamba's per-word timesteps significantly predict human reading times beyond GPT-2 surprisal in a naturalistic dataset.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Both humans and LLMs trust content more when labeled human-authored than AI-generated, with LLMs showing denser attention to labels and higher uncertainty under AI labels, mirroring human heuristic patterns.
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
-
Timesteps of Mamba Align with Human Reading Times
Mamba's per-word timesteps significantly predict human reading times beyond GPT-2 surprisal in a naturalistic dataset.
-
Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge
Both humans and LLMs trust content more when labeled human-authored than AI-generated, with LLMs showing denser attention to labels and higher uncertainty under AI labels, mirroring human heuristic patterns.
-
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.