Incremental Speciation in Evolutionary Red Teaming of Large Language Models

Speciation maintains distinct subpopulations in evolutionary search through similarity-based grouping and species-aware parent selection. For text-based individuals, niches depend on both the compatibility representation and the assignment operator that turns pairwise relations into species. We examine this design space in black-box evolutionary red teaming of large language models, comparing embedding and natural language inference (NLI) dissimilarities under representative-based and density-based speciation. Offline calibration on a 3,139-prompt archive shows that MiniLM embedding dissimilarity ($d_E$) and DeBERTa-v3-small NLI non-entailment ($d_{\neg E}$) produce different species structures at the same nominal threshold. Even with pairwise edge density matched to MiniLM, NLI density connectivity forms a few concentrated, mixed-topic species, with substantially more off-topic membership. These structural differences persist online under a matched evaluation budget. The endpoint top-50 median fitness favors incremental DBSCAN over leader-follower, but bootstrap intervals from 10 runs include zero, providing no reliable evidence of an advantage. Semantic diversity among top prompts declines in every configuration, with no consistent method advantage. The clearest difference concerns high-fitness population occupancy: MiniLM incremental DBSCAN maintains mature niches across seed topics, whereas NLI incremental DBSCAN attains the same highest observed median fitness while concentrating high-fitness prompts in variants of a few seed topics. Thus, representation-dependent connectivity predicts population structure more consistently than endpoint fitness. Species count alone does not establish quality-diversity, and more species do not necessarily preserve semantically diverse high-fitness prompts.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.23949
Primary Topic
Evolutionary Algorithms and Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Incremental Speciation in Evolutionary Red Teaming of Large Language Models

Travis Desell, Onkar Eknath Shelar
arXiv (Cornell University)
Evolutionary Algorithms and Applications
preprint

Incremental Speciation in Evolutionary Red Teaming of Large Language Models

Travis Desell, Onkar Eknath Shelar
preprint en

Abstract

Speciation maintains distinct subpopulations in evolutionary search through similarity-based grouping and species-aware parent selection. For text-based individuals, niches depend on both the compatibility representation and the assignment operator that turns pairwise relations into species. We examine this design space in black-box evolutionary red teaming of large language models, comparing embedding and natural language inference (NLI) dissimilarities under representative-based and density-based speciation. Offline calibration on a 3,139-prompt archive shows that MiniLM embedding dissimilarity ($d_E$) and DeBERTa-v3-small NLI non-entailment ($d_{\neg E}$) produce different species structures at the same nominal threshold. Even with pairwise edge density matched to MiniLM, NLI density connectivity forms a few concentrated, mixed-topic species, with substantially more off-topic membership. These structural differences persist online under a matched evaluation budget. The endpoint top-50 median fitness favors incremental DBSCAN over leader-follower, but bootstrap intervals from 10 runs include zero, providing no reliable evidence of an advantage. Semantic diversity among top prompts declines in every configuration, with no consistent method advantage. The clearest difference concerns high-fitness population occupancy: MiniLM incremental DBSCAN maintains mature niches across seed topics, whereas NLI incremental DBSCAN attains the same highest observed median fitness while concentrating high-fitness prompts in variants of a few seed topics. Thus, representation-dependent connectivity predicts population structure more consistently than endpoint fitness. Species count alone does not establish quality-diversity, and more species do not necessarily preserve semantically diverse high-fitness prompts.

arXiv (Cornell University)
Evolutionary Algorithms and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon