Pairwise Ranking Prompting (PRP): Zero-shot LLM reranking library implementing efficient pairwise strategies (Heapsort, Sliding Window, All-Pairs). Mitigates position bias via bidirectional comparison and ensures reliability with structured Pydantic validation. Built for Haystack pipelines.

Agentic Graph RAG for Medical diagnosis and Clinical QA. Combines LangGraph-orchestrated multi-hop reasoning with parallel semantic/relational retrieval, Neo4j knowledge graphs, and vector search for evidence-grounded answers on MedQA, MedXpertQA, MedCaseReasoning and MMLU-Pro.

Advanced LLM fine-tuning techniques: SFT (LoRA, QLoRA, DoRA, P-/Prefix-Tuning), GRPO, DPO, ORPO, KTO & PPO; composable correctness/format rewards + LLM-as-a-Judge evals (DeepEval, Evidently AI) across math, multi-hop, medical & general QA on Llama 3, Mistral, Phi-4, Gemma & Qwen3. Built on TRL, PEFT & Unsloth.

LLM-Blender: Ensembling framework that maximizes LLM performance via pairwise ranking. Employs PairRanker to rank candidates and GenFuser to merge outputs, generating superior responses by combining the diverse strengths of multiple open-source models.

Group Relative Policy Optimization (GRPO) implementations - NanoAhaMoment, GRPO:Zero, Simple GRPO, and GRPO from Scratch - spanning vLLM + DeepSpeed, custom Transformer stack, Bottle HTTP reference server, and pure PyTorch. Compares generation backends, reference policy strategies, reward designs, and loss functions on GSM8K and Countdown tasks.

Production-ready Haystack/LangChain pipelines for Hybrid & Parent-Child Retrieval, Diversity Filtering, MMR, Metadata Filtering, Reranking, Query Enhancement, Multi-Tenancy, Agentic RAG across Pinecone, Weaviate, Milvus, Qdrant, Chroma with dataset loaders, evaluation tooling, and benchmarks for TriviaQA, ARC, PopQA, FactScore and Earnings Calls.

Medical Reasoning Evaluation

Modular LLM ranking library for Information Retrieval and RAG. Implements state-of-the-art Pairwise, Setwise, and Listwise ranking with structured generation and specialized models (RankZephyr, RankLlama). Features efficient sorting algorithms, sliding windows, and zero-shot capabilities.

Self-Reflective Question Answering for Biomedical Reasoning. GRPO fine-tuning via QLoRA & Unsloth with rewards for correctness, relevance, groundness, utility & XML structure. Structured think → answer → self-reflection with context grading, relevance assessment & groundness evaluation. DeepEval LLM-as-a-Judge (GEval, Faithfulness, Relevancy).