Search papers, labs, and topics across Lattice.
This paper evaluates the performance of DS@GT ARC's submission to the CLEF 2026 LongEval Task 4, focusing on the integrity of citations in Retrieval-Augmented Generation (RAG) QA systems. By implementing a corrective pipeline using Corrective RAG (CRAG) and CiteFix, the authors demonstrate that while frontier models excel in relevance and fluency, they often fail to utilize context effectively, leading to issues in citation faithfulness. The findings suggest that traditional evaluation metrics may overlook critical aspects of trustworthiness, advocating for metrics that prioritize strict answer grounding in RAG QA evaluations.
Frontier models may sound fluent, but they often ignore context, risking citation integrity in RAG QA systems.
This paper describes DS@GT ARC's submission to the CLEF 2026 LongEval Task 4 on Retrieval-Augmented Generation (RAG). In this submission, we examine a divergence between traditional natural language evaluation metrics and citation integrity as applied to RAG QA systems. We evaluate a corrective pipeline using Corrective RAG (CRAG) and CiteFix against baseline and frontier model benchmark RAG QA scores. While frontier models maximized answer relevance and fluency scores, our RAGAs LLM-as-judge diagnostics indicate that frontier models would correctly identify relevant documents without using their context in answer generation. Conversely, by filtering chunks pre-generation and enforcing strict entailment of generated claims to the cited material post-generation, our corrective pipeline marginally improved citation faithfulness and answer grounding. We propose that evaluation of trustworthy RAG QA requires metrics that reward strict answer grounding.
