AI & ML interests
RAG, LLM, Chunking, Distillation, Multi-hop Systems, Artificial Intelligence
Recent Activity
Papers
View all Papers
Organization Card
SightAndCite
Retrieval that sees the structure and cites the evidence.
Open research on retrieval-augmented generation (RAG), chunking, multi-hop reasoning and efficient LLM systems.
🔭 Featured: SpectRAG
Stop retrieving chunks. Start retrieving context. SpectRAG replaces independent top-k ranking with context-set selection over a weighted chunk graph and its Laplacian spectrum. It returns evidence that is relevant, diverse and connected, all under a fixed token budget.
| 📄 Paper | arXiv:2610.36991 · 🤗 Paper page |
| 🎬 Visual walkthrough | sightandcite/SpectRAG |
| 📊 Evaluation results | sightandcite/SpectRAG-eval-results |
| 💻 Code (MIT) | github.com/SightAndCite/SpectRAG |
Highlights on MultiHopRAG & UltraDomain
- 91.8% overall gold-evidence recall (next best 76.1%)
- 95.1% exact match on inference questions
- ~6× smaller index than LightRAG (46 MB vs 274 MB)
- LLM judges prefer SpectRAG's answers for diversity against every baseline
🧭 What we work on
- Retrieval-augmented generation: context-set selection, hybrid retrieval, graph-based RAG
- Chunking: structure-aware and semantic segmentation for long documents
- Multi-hop systems: recovering bridge evidence across chunks and documents
- Efficient LLM pipelines: distillation, lightweight indexes, fully local deployments
👥 Team
Zafer Sahinoglu · Abdulazeez Mohammed · Buse Yaren Kazangirler · Cahit Berkay Kazangirler
📬 Get in touch
Questions, ideas or a retriever that breaks in interesting ways? Open a discussion on the paper page or an issue on GitHub.
models 0
None public yet