6 papers
Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use
Adeyemi Adeseye, Aisvarya Adeseye, Hannu Tenhunen +1
Users often exhibit changes in interaction behavior before explicitly seeking assistance, enabling systems to anticipate future assistance use. This is especially important in high…
CARE-SD: Explainable Reasoning Architecture for Local SLM Self-Disclosure Analysis in Textual Data
Aisvarya Adeseye, Adeyemi Adeseye, Mohammad Tahir +1
Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured by conventional technical assessments. Consequently, identi…
Parallel LLM Reasoning for Bias-Resilient, Robust Conceptual Abstraction
Aisvarya Adeseye, Jouni Isoaho, Adeyemi Adeseye
Large language models (LLMs) have been increasingly used to analyze text. However, they are often plagued with contextual reasoning limitations when analyzing long documents. When…
Improving Quantized Model Performance in Qualitative Analysis with Multi-Pass Prompt Verification
Aisvarya Adeseye, Jouni Isoaho, Adeyemi Adeseye
Quantized Large Language Models (LLMs) are used more often in qualitative analysis because they run fast and need fewer computing resources. This study examines how different lower…
Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on the TruthfulQA Benchmark
Adeyemi Adeseye, Aisvarya Adeseye, Hannu Tenhunen +1
Small language models (SLMs) have been increasingly deployed in edge devices and other resource-constrained settings. However, these models make confident mispredictions and produc…
A Prompt-Based Framework for Loop Vulnerability Detection Using Local LLMs
Adeyemi Adeseye, Aisvarya Adeseye
Loop vulnerabilities are one major risky construct in software development. They can easily lead to infinite loops or executions, exhaust resources, or introduce logical errors tha…