ARES

Automated RAG Evaluation System, for evaluating RAG systems along the dimensions of context relevance, answer faithfulness, and answer relevance. By creating its own synthetic training data, ARES finetunes lightweight LM judges to assess the quality of individual RAG components. To mitigate potential prediction errors, ARES utilizes a small set of human-annotated datapoints for prediction-powered inference (PPI)

References

• ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems

---

Backlinks

• Facts as a Function