-
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
Paper • 2411.06208 • Published • 16 -
Instruction Following without Instruction Tuning
Paper • 2409.14254 • Published • 27 -
Toward General Instruction-Following Alignment for Retrieval-Augmented Generation
Paper • 2410.09584 • Published • 45
Dmitriev
Danil
AI & ML interests
NLP, Multilingual, mLM, Dialog systems, Graph NN
Organizations
None yet
Collections
9
-
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Paper • 2310.11511 • Published • 74 -
PEARL: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers
Paper • 2311.09180 • Published • 7 -
Enhancing Structured-Data Retrieval with GraphRAG: Soccer Data Case Study
Paper • 2409.17580 • Published • 7 -
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Paper • 2410.08815 • Published • 41
models
None public yet
datasets
None public yet