8 papers
Super Weights in LLMs and the Failure of Selective Training
Shreyas Subramanian, Adewale Akinfaderin, Akarsha Sehwag
Recent work identified Super Weights, individual parameters whose removal degrades model performance by orders of magnitude. We show that this degradation due to pruning Super Weig…
FregeLogic at SemEval 2026 Task 11: A Hybrid Neuro-Symbolic Architecture for Content-Robust Syllogistic Validity Prediction
Adewale Akinfaderin, Nafi Diallo
We present FregeLogic, a hybrid neuro-symbolic system for SemEval-2026 Task 11 (Subtask 1), which addresses syllogistic validity prediction while reducing content effects on predic…
Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use
Shreyas Subramanian, Adewale Akinfaderin, Yanyan Zhang +4
While Retrieval-Augmented Generation (RAG) has proven effective for generating accurate, context-based responses based on existing knowledge bases, it presents several challenges i…
VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation
Adewale Akinfaderin, Shreyas Subramanian
Financial AI systems suffer from a critical blind spot: while Retrieval-Augmented Generation (RAG) excels at finding relevant documents, language models still generate calculation…
Plan-and-Write: Structure-Guided Length Control for LLMs without Model Retraining
Adewale Akinfaderin, Shreyas Subramanian, Akarsha Sehwag
Length control in Large Language Models (LLMs) is a crucial but under-addressed challenge, with applications ranging from voice interfaces requiring concise responses to research s…
User-Based Sequential Modeling with Transformer Encoders for Insider Threat Detection
Mohamed Elbasheer, Adewale Akinfaderin
Insider threat detection presents unique challenges due to the authorized status of malicious actors and the subtlety of anomalous behaviors. Existing machine learning methods ofte…