Agenda-based Narrative Extraction: Steering Pathfinding Algorithms with Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912992116867072 |
|---|---|
| author | Keith-Norambuena, Brian Felipe Rojas-Córdova, Carolina Inés Meneses-Villegas, Claudio Juvenal Lam-Esquenazi, Elizabeth Johanna Flores-Bustos, Angélica María Molina-Villablanca, Ignacio Alejandro Leyton-Vallejos, Joshua Emanuel |
| author_facet | Keith-Norambuena, Brian Felipe Rojas-Córdova, Carolina Inés Meneses-Villegas, Claudio Juvenal Lam-Esquenazi, Elizabeth Johanna Flores-Bustos, Angélica María Molina-Villablanca, Ignacio Alejandro Leyton-Vallejos, Joshua Emanuel |
| contents | Existing narrative extraction methods face a trade-off between coherence, interactivity, and multi-storyline support. Narrative Maps supports rich interaction and generates multiple storylines as a byproduct of its coverage constraints, though this comes at the cost of individual path coherence. Narrative Trails achieves high coherence through maximum capacity path optimization but provides no mechanism for user guidance or multiple perspectives. We introduce agenda-based narrative extraction, a method that bridges this gap by integrating large language models into the Narrative Trails pathfinding process to steer storyline construction toward user-specified perspectives. Our approach uses an LLM at each step to rank candidate documents based on their alignment with a given agenda while maintaining narrative coherence. Running the algorithm with different agendas yields different storylines through the same corpus. We evaluated our approach on a news article corpus using LLM judges with Claude Opus 4.5 and GPT 5.1, measuring both coherence and agenda alignment across 64 endpoint pairs and 6 agendas. LLM-driven steering achieves 9.9% higher alignment than keyword matching on semantic agendas (p=0.017), with 13.3% improvement on \textit{Regime Crackdown} specifically (p=0.037), while keyword matching remains competitive on agendas with literal keyword overlap. The coherence cost is minimal: LLM steering reduces coherence by only 2.2% compared to the agenda-agnostic baseline. Counter-agendas that contradict the source material score uniformly low (2.2-2.5) across all methods, confirming that steering cannot fabricate unsupported narratives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29661 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Agenda-based Narrative Extraction: Steering Pathfinding Algorithms with Large Language Models Keith-Norambuena, Brian Felipe Rojas-Córdova, Carolina Inés Meneses-Villegas, Claudio Juvenal Lam-Esquenazi, Elizabeth Johanna Flores-Bustos, Angélica María Molina-Villablanca, Ignacio Alejandro Leyton-Vallejos, Joshua Emanuel Computation and Language Artificial Intelligence Information Retrieval Existing narrative extraction methods face a trade-off between coherence, interactivity, and multi-storyline support. Narrative Maps supports rich interaction and generates multiple storylines as a byproduct of its coverage constraints, though this comes at the cost of individual path coherence. Narrative Trails achieves high coherence through maximum capacity path optimization but provides no mechanism for user guidance or multiple perspectives. We introduce agenda-based narrative extraction, a method that bridges this gap by integrating large language models into the Narrative Trails pathfinding process to steer storyline construction toward user-specified perspectives. Our approach uses an LLM at each step to rank candidate documents based on their alignment with a given agenda while maintaining narrative coherence. Running the algorithm with different agendas yields different storylines through the same corpus. We evaluated our approach on a news article corpus using LLM judges with Claude Opus 4.5 and GPT 5.1, measuring both coherence and agenda alignment across 64 endpoint pairs and 6 agendas. LLM-driven steering achieves 9.9% higher alignment than keyword matching on semantic agendas (p=0.017), with 13.3% improvement on \textit{Regime Crackdown} specifically (p=0.037), while keyword matching remains competitive on agendas with literal keyword overlap. The coherence cost is minimal: LLM steering reduces coherence by only 2.2% compared to the agenda-agnostic baseline. Counter-agendas that contradict the source material score uniformly low (2.2-2.5) across all methods, confirming that steering cannot fabricate unsupported narratives. |
| title | Agenda-based Narrative Extraction: Steering Pathfinding Algorithms with Large Language Models |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2603.29661 |