A Framework for LLM-Assisted Smart Policing System
Bibliographic record
Abstract
In the face of rapidly increasing crime rates, the evolving complexity of crime data processing, and public safety challenges, the need for more advanced policing solutions has increased leading to the emergence of smart policing systems and predictive policing techniques. This urgency and shift toward smart policing incorporates artificial intelligence (AI), with a specific focus on machine learning (ML) as an essential tool for data analysis, pattern recognition, and proactive crime forecasting. Among these, the flexibility and power of AI techniques including large language models (LLMs), as a subset of generative AI, have increased the interest in applying them in real-world applications, such as financial, medical, legal, and agricultural applications. However, the abilities and possibilities of adopting LLMs in applications including crime prediction remain unexplored. This paper focuses on bridging this gap by developing a framework based on the transformative potential of BART, GPT-3, and GPT-4, three state-of-the-art LLMs, in the domain of smart policing, specifically, crime prediction. As a prototype, diverse methods such as zero-shot prompting, few-shot prompting, and fine-tuning are used to comprehensively assess the performance of these models in crime prediction based on state-of-the-art datasets from two major cities: San Francisco and Los Angeles. The main objective is to illuminate the adaptability of LLMs and their capacity to revolutionize crime analysis practices. Additionally, a comparative analysis of the aforementioned methods on the GPT series model and BART with ML techniques is provided which shows that the GPT models are more suitable than the traditional ML models for crime classification in most experimental scenarios.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".