3 papers
cs.CL2026
Probe, Don't Prompt: A Hidden-State Probe for Metadata Filtering in Multi-Meta-RAG
Mykhailo Poliakov, Nadiya Shvai
Multi-Meta-RAG improves retrieval for multi-hop question answering by filtering a vector store on metadata (the news source) that it extracts from each query by prompting gpt-3.5-t…
cs.CL2025
MisSynth: Improving MISSCI Logical Fallacies Classification with Synthetic Data
Mykhailo Poliakov, Nadiya Shvai
Health-related misinformation is very prevalent and potentially harmful. It is difficult to identify, especially when claims distort or misinterpret scientific findings. We investi…
cs.CL2024
Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata
Mykhailo Poliakov, Nadiya Shvai
The retrieval-augmented generation (RAG) enables retrieval of relevant information from an external knowledge source and allows large language models (LLMs) to answer queries over…