Q-RAG: Long Context Multi‑Step Retrieval via Value‑Based Embedder Training

ICLROral2026

Authors
Artyom Sorokin, Nazar Buzun, Aleksandr Anokhin, Egor KONSTANTINOVICH VEDERNIKOV, Petr Anokhin, Mikhail Burtsev, Evgeny Burnaev
Affiliation
Applied AI Institute
Venue
ICLR 2026
Track
Oral

TL;DR

Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most existing RAG methods focus on single-step retrieval, which is often insufficient for answering complex questions that require multi-step search.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

hallucination long context efficient retrieval llm rag

Related ICLR papers

← All ICLR 2026 Oral papers · Browse the whole archive