RAFT (Retrieval Augmented Fine-Tuning)
Fine-tuning technique that trains models to answer questions using retrieved context documents.
Retrieval Augmented Fine-Tuning (RAFT) is a training methodology that teaches language models how to effectively use retrieved documents when answering domain-specific questions. Standard fine-tuning trains a model on question-answer pairs alone. RAFT exposes the model during training to a mix of relevant and irrelevant retrieved documents alongside each question. This trains the model to learn which information is useful, how to extract key facts from supporting context, and how to ignore distractors. These skills are essential for reliable performance in retrieval-augmented generation (RAG) pipelines.
The mechanics of RAFT involve constructing training examples that pair each question with a set of retrieved passages, some of which are genuinely relevant ("oracle" documents) and some of which are deliberately unhelpful noise. The model is trained to produce answers that cite or reason from the correct passages while disregarding the irrelevant ones. Standard RAG setups hand retrieved documents to a pre-trained or instruction-tuned model at inference time without ever having explicitly trained that model to handle noisy, multi-document context.
RAFT closes a gap between how models are trained and how they are deployed. A model fine-tuned on clean question-answer pairs may struggle when suddenly presented with a cluttered retrieval result at inference time. By simulating realistic retrieval conditions during fine-tuning, RAFT produces models that are substantially more robust and accurate in production RAG systems. This is especially valuable in enterprise and domain-specific applications, such as medical, legal, or technical documentation, where precision and source fidelity are critical.
The approach was formally introduced by researchers at UC Berkeley in 2024. It builds on earlier work in retrieval-augmented generation and domain adaptation. RAFT is a practical bridge between fine-tuning for specialization and retrieval for knowledge grounding, and has quickly become an influential recipe for building reliable, knowledge-intensive AI assistants.
Research this in Signals
Signals turns a topic into a sourced research record you can inspect and rerun. Your first scan is free, and this one starts with RAFT (Retrieval Augmented Fine-Tuning) already loaded, so edit it or scan as is.
