@inproceedings{li-etal-2026-efficiency,
    title = "Efficiency vs. Verifiability in Evidence-Aware {RAG}: Does Prompt Compression Preserve Citation Grounding?",
    author = "Li, Aiyu  and
      Peng, Qian  and
      Chen, Bin",
    editor = "Mysore, Sheshera  and
      Kumar, Sachin  and
      Balachandran, Vidhisha  and
      Hayati, Shirley Anugrah  and
      Brahman, Faeze  and
      Moussa, Hanane Nour  and
      Salemi, Alireza",
    booktitle = "Proceedings of the Second Workshop on Customizable {NLP}: Progress and Challenges in Customizing {NLP} for a Domain, Application, Group, or Individual ({C}ustom{NLP}4{U})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.customnlp4u-1.19/",
    pages = "202--215",
    ISBN = "979-8-89176-396-8",
    abstract = "Retrieval-augmented generation (RAG) is widely used in domain-specific and knowledge-intensive applications, where long prompts increase inference cost and may exceed context limits. Prompt compression is therefore appealing, but existing evaluations focus primarily on answer quality, overlooking whether compressed systems remain faithful to the retrieved evidence. In this paper, we ask: does compression that preserves answers also preserve grounding? Using Self-RAG and LLMLingua-2 in a controlled setting, we evaluate compressed RAG on ASQA in terms of both answer correctness and citation grounding. Under increasing compression, answer correctness drops by only 2-4{\%}, whereas grounding drops by 40-50{\%}. This stark divergence shows that answer-only evaluation can substantially overestimate the reliability of compressed RAG in evidence-aware scenarios. We further propose a lightweight hierarchical compression strategy that prioritizes evidence-bearing spans. It recovers nearly all grounding loss while maintaining comparable answer quality. Our results reveal a clear trade-off between efficiency and verifiability, and suggest that compression in RAG should be customized to downstream verification needs rather than treated as a one-size-fits-all efficiency intervention."
}