Tag
This paper introduces KGCQual, an interpretable metric for evaluating the quality of automatically constructed knowledge graphs by assessing entity and relation faithfulness to source text, and demonstrates its correlation with downstream performance.
This paper presents an empirical study adapting the small language model Phi Silica for short-form text rewriting through dataset curation, prompt distillation, and parameter-efficient fine-tuning, showing that targeted adaptation significantly improves semantic fidelity and reduces hallucinations.