LLM-based Intelligent Literature Review Assistant
08.05.2025Develop a semi-automated assistant for structured literature reviews, combining LLMs, citation graph search, and spreadsheet-based curation. This project builds on an existing prototype with basic PDF parsing, citation crawling, and initial LLM integration.
Objective:
Adapt the existing CIDDS simulation environment so that system and network logs are forwarded directly into the Elastic Stack. Evaluate logging tools (e.g., Winlogbeat, Filebeat, Auditbeat) and configure them for simulated environments.
Betreuer: Daniel Schlör
Key Tasks:
- Design and implement a web-frontend with Google Sheets export for controlling and reviewing the literature extraction process
- Develop selection and prioritization strategies for related papers (via LLM or keyword heuristics)
- Highlight extracted content semantically in PDFs and provide PDF browsing support
- Evaluate different prompting and extraction strategies in a small-scale user study
Extension Directions (Master Thesis / Practica):
- LLM Strategy Benchmarking
- Agent-Based Literature Curation
- Citation Graph Navigation and Topic Evolution
- Dynamic Prompt Engineering via Meta-Learning
