MTP induces representational contractivity for coherent world models in LLMs but causes illegal latent shortcuts; LSE-MTP anchors to true trajectories to reduce hallucinations and improve consistency.
InProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18669–18680, Miami, Florida, USA
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement
MTP induces representational contractivity for coherent world models in LLMs but causes illegal latent shortcuts; LSE-MTP anchors to true trajectories to reduce hallucinations and improve consistency.