arXiv subjects

Syeda Kisaa Fatima

Publications and source records attributed to Syeda Kisaa Fatima.

3 recordsLinked to original sources

arXiv2026

Not All Claims Are Equally Risky: FACTOR for Adaptive Verification in Factual Long-Form Generation

Large Language Models (LLMs) generate fluent long-form text, however, often add unsupported factual claims. Existing verification techniques improve factuality by grounding generation in external evidence. However, the same verification policy usually applies to all claims despite being differences in hallucination risks. We propose \textit{FACTOR} (\textit{FACTuality-Oriented Risk-aware Verification}), an inference-time model that adapts verification criteria according to claim-level uncertainty. FACTOR combines uncertainty estimation, adaptive language inference verification, and candidate re-ranking to allocate verification effort where it is most needed. We evaluate \textit{FACTOR} on FactScore benchmark showing that adaptive verification improves factuality while reducing verification cost simultaneously. We further perform different ablation studies to identify the primary driver of these gains. Our results show the effective and model-agnostic performance of \textit{FACTOR} for improving factuality in long-form generation.

cs.CL↗

arXiv2026

Crime Hotspot Prediction Using Deep Graph Convolutional Networks

Crime hotspot prediction is critical for ensuring urban safety and effective law enforcement, it remains challenging due to complex spatial dependencies that are inherent in criminal activities. The traditional approaches use classical algorithms such as the KDE and SVM to model data distributions and decision boundaries. The methods often fail to capture these spatial relationships, treating crime events as independent and ignoring geographical interactions. To address this, we propose a novel framework based on Graph Convolutional Networks (GCNs), which explicitly model all of spatial dependencies by representing crime data as a graph. In this graph, nodes represent discrete geographic grid cells and edges capture proximity relationships. The spatial features from Chicago Crime Dataset are used in this system, a multi-layer GCN model is trained to classify crime types and predict high-risk zones. Our approach significantly outperforms traditional approaches, achieving 78% classification accuracy. Moreover, the model generates interpretable heat maps of crime hotspots, demonstrating the usefulness of graph-based learning for predictive policing and spatial criminology.

cs.LG↗

arXiv2025

AutoGen Driven Multi Agent Framework for Iterative Crime Data Analysis and Prediction

This paper introduces LUCID-MA (Learning and Understanding Crime through Dialogue of Multiple Agents), an innovative AI powered framework where multiple AI agents collaboratively analyze and understand crime data. Our system that consists of three core components: an analysis assistant that highlights spatiotemporal crime patterns; a feedback component that reviews and refines analytical results; and a prediction component that forecasts future crime trends. With a well-designed prompt and the LLaMA-2-13B-Chat-GPTQ model, it runs completely offline and allows the agents undergo self-improvement through 100 rounds of communication with less human interaction. A scoring function is incorporated to evaluate agent performance, providing visual plots to track learning progress. This work demonstrates the potential of AutoGen-style agents for autonomous, scalable, and iterative analysis in social science domains, maintaining data privacy through offline execution. It also showcases a computational model with emergent intelligence, where the system's global behavior emerges from the interactions of its agents. This emergent behavior manifests as enhanced individual agent performance, driven by collaborative dialogue between the LLM-based agents.

cs.MA↗