CRISTOBAL MISSANA DAVILA

Ms. CRISTOBAL MISSANA DAVILA

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 October 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
BGBady Gana
Bady Gana
Wenceslao PalmaWenceslao Palma
Wenceslao Palma
Freddy A. LucayFreddy A. Lucay
Freddy A. Lucay
CDCRISTOBAL MISSANA DAVILA
CRISTOBAL MISSANA DAVILA
CSCarlos Jesús Abarza Suazo
Carlos Jesús Abarza Suazo
HAHector Allende-Cid
Hector Allende-Cid
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 τ=0.2 as optimal, which stabilized results (sd =0.12) and improved robustness relative to retrieval baselines (ΔEG=+0.08, Δρ=+0.55). 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.