Linguistic Structure Enrichment Fails to Improve Text Coherence
Recent studies have shown that while large language models (LLMs) can produce grammatically correct text, they often struggle with semantically coherent output. This article investigates whether adding syntactic and rhetorical information could improve the LLMs' ability to assess coherence. The research found that plain texts performed better because the added information did not align well with…
1 source primary source
Key points
- Linguistic structure enrichment did not improve text coherence
- Plain texts outperformed enriched texts due to structural mismatch
- Coherence assessment can serve as a proxy for detecting misleading content
Read the original at arXiv cs.CL · by Victor Mazzotti, Luiz Pereira, Marina Bitencourt dos Santos, Helena Maia, Carlos Caetano, N\'adia Felix, Sandra Avila primary source Open source ↗
Topics · follow one to build your own front page
Linguistic Structure EnrichmentLarge Language Models
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us.
More in Research
All →- Guide: How AI Embeddings Encode Meaning into Numerical Vectors · 1 src
- LLM-Anchored Paralinguistic Boost for Alzheimer's Detection · 1 src
- New probability-wave framework links trader behavior to AGI architecture design · 1 src
- Data-Efficient Language Modeling Advances · 1 src
- MAAGL framework improves graph reasoning with multi-agent collaboration · 1 src
Comments
via GitHub Discussions