CACarlos Abarza
Carlos Abarza
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Carlos Abarza has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Bady Gana
Escuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Avenida Brasil 2241, Valparaíso 2362807, Chile
1 shared publication - Cristóbal Missana
Escuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Avenida Brasil 2241, Valparaíso 2362807, Chile
1 shared publication - Freddy A. Lucay
Escuela de Ingeniería Química, Pontificia Universidad Católica de Valparaíso, Avenida Brasil, Valparaíso 2162, Chile
1 shared publication - Héctor Allende
Escuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Avenida Brasil 2241, Valparaíso 2362807, Chile
1 shared publication - Wenceslao Palma
Escuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Avenida Brasil 2241, Valparaíso 2362807, Chile
1 shared publication
Latest Publications
- Open Access
- 31 October 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (21) , 3472
Measuring Semantic Coherence of RAG-Generated Abstracts Through Complex Network Metrics
The exponential growth of scientific literature demands scalable methods to evaluate large-language-model outputs beyond surface-level fluency. We present a two-phase framework that separates generation from evaluation: a retrieval-augmented generation system first produces candidate abstracts, which are then embedded into semantic co-occurrence graphs and assessed using seven robustness metrics from complex network theory. Two experiments were conducted. The first varied model, embedding and prompt configurations, achieved results showing clear differences in performance; the best family combined gemma-2b-it, a prompt inspired by chain-of-Thought reasoning, and all-mpnet-base-v2, achieving the highest graph-based robustness. The second experiment refined the temperature setting for this family, identifying as optimal, which stabilized results (sd ) and improved robustness relative to retrieval baselines (, ). While human evaluation was limited to a small set of abstracts, the results revealed a partial convergence between graph-based robustness and expert judgments of coherence and importance. Our approach contrasts with methods like GraphRAG and establishes a reproducible, model-agnostic pathway for the scalable quality control of LLM-generated scientific content.- 31 October 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (21) , 3472
Open AccessMeasuring Semantic Coherence of RAG-Generated Abstracts Through Complex Network Metrics
The exponential growth of scientific literature demands scalable methods to evaluate large-language-model outputs beyond surface-level fluency. We present a two-phase framework that separates generation from evaluation: a retrieval-augmented generation system first produces candidate abstracts, which are then embedded into semantic co-occurrence graphs and assessed using seven robustness metrics from complex network theory. Two experiments were conducted. The first varied model, embedding and prompt configurations, achieved results showing clear differences in performance; the best family combined gemma-2b-it, a prompt inspired by chain-of-Thought reasoning, and all-mpnet-base-v2, achieving the highest graph-based robustness. The second experiment refined the temperature setting for this family, identifying as optimal, which stabilized results (sd ) and improved robustness relative to retrieval baselines (, ). While human evaluation was limited to a small set of abstracts, the results revealed a partial convergence between graph-based robustness and expert judgments of coherence and importance. Our approach contrasts with methods like GraphRAG and establishes a reproducible, model-agnostic pathway for the scalable quality control of LLM-generated scientific content.