Research
Accepted
-
Biologically Inspired Document Embedding in Discrete Spaces
Discrete semantic grid mapping of document embeddings, benchmarked against PCA, t-SNE, and UMAP.
-
Divergent Framings: Persona-Dependent LLM Responses on Antisemitism-Adjacent Issues
Post-deployment: persona-driven behavioral bias evaluation across LLMs (15,552 personas).
In Progress
-
FAAR: Failure-Aware Agentic Retrieval
Typed failure diagnosis and targeted recovery for OCR-heavy document QA pipelines.
Projects
Some of the things I did :)
-
Agent Autopsy↗
Local-first debugger for LLM agent pipelines. Ingests traces, auto-detects 10+ failure classes, surfaces fixes via CLI, Streamlit, and MCP.
-
EngageMind↗
Full-stack RAG platform with LoRA fine-tuning, stateful memory, and hallucination mitigation. BSc thesis.
-
AuditLens↗
Dataset-level fairness checks for tabular ML with statistical tests and optional LLM interpretation.
-
FailSafeRAG↗
OCR + RAG pipeline that handles extraction failures gracefully for document QA, related to ongoing FAAR work.
-
Multi-Agent Reflection Engine (Forkpoint)↗
Five-agent reflection system with eval pipeline and audit snapshots.