MAGNET multi-agent generation with persona grounding and ATLAS graph verification yields 34-50% fewer hallucinations and annotations than single-model or IBSEN baselines at 100-page scale.
Computational Linguistics34(1):1–34
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 3roles
background 1polarities
background 1representative citing papers
SAGE achieves 98.8% score convergence and over 94% inter-rater agreement on 100 stories, statistically confirming canonical works outperform pulp fiction and LLM-generated narratives especially in cultural critique and philosophical depth.
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.
citing papers explorer
-
From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives
MAGNET multi-agent generation with persona grounding and ATLAS graph verification yields 34-50% fewer hallucinations and annotations than single-model or IBSEN baselines at 100-page scale.
-
SAGE: Hierarchical LLM-Based Literary Evaluation through Ontology-Grounded Interpretive Dimensions
SAGE achieves 98.8% score convergence and over 94% inter-rater agreement on 100 stories, statistically confirming canonical works outperform pulp fiction and LLM-generated narratives especially in cultural critique and philosophical depth.
-
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.