6 papers
Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns
Afshin Khadangi
Large language models deployed in the wild must adapt to evolving data, user behavior, and task mixtures without erasing previously acquired capabilities. In practice, this remains…
When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models
Afshin Khadangi, Hanna Marxen, Amir Sartipi +2
Frontier language models increasingly participate in conversations about distress and mental health, yet the mechanisms that generate anthropomorphic self narratives remain unclear…
Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning
Afshin Khadangi, Amir Sartipi, Igor Tchappi +2
The tension between data privacy and model utility has become the defining bottleneck for the practical deployment of large language models (LLMs) trained on sensitive corpora incl…
KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text Classification
Qianbo Zang, Christophe Zgrzendek, Igor Tchappi +2
Hierarchical Text Classification (HTC) involves assigning documents to labels organized within a taxonomy. Most previous research on HTC has focused on supervised methods. However,…
Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models
Afshin Khadangi, Amir Sartipi, Igor Tchappi +1
Large language models (LLMs) often produce inaccurate or misleading content-hallucinations. To address this challenge, we introduce Noise-Augmented Fine-Tuning (NoiseFiT), a novel…
CognArtive: Large Language Models for Automating Art Analysis and Decoding Aesthetic Elements
Afshin Khadangi, Amir Sartipi, Igor Tchappi +1
Art, as a universal language, can be interpreted in diverse ways, with artworks embodying profound meanings and nuances. The advent of Large Language Models (LLMs) and the availabi…