Metraipolis › archive › dc_d6f0ed2dd207

Attributable Post-Rationalization in RAG Citations: A Controlled Reproduction and an RLVR Comparison — arXiv:2609.23053

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23053
License (as archived)
CC0-1.0
Archived
2026-10-09T06:49:42.630Z
SHA-256 of the archived text
5ced46d4ddfab319824683b09fc2d8debc488d06a2b56cf5f507a366773fe5d6
Stable URL of this page
https://metraipolis.com/documento/dc_d6f0ed2dd207

How to cite

Attributable Post-Rationalization in RAG Citations: A Controlled Reproduction and an RLVR Comparison — arXiv:2609.23053 — arXiv (en), https://arxiv.org/abs/2609.23053 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d6f0ed2dd207 (Metraipolis archive dc_d6f0ed2dd207, sha256 5ced46d4ddfab319824683b09fc2d8debc488d06a2b56cf5f507a366773fe5d6)
BibTeX
@misc{dcd6f0ed2dd207,
  title = {Attributable Post-Rationalization in RAG Citations: A Controlled Reproduction and an RLVR Comparison — arXiv:2609.23053},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23053},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d6f0ed2dd207; sha256 5ced46d4ddfab319824683b09fc2d8debc488d06a2b56cf5f507a366773fe5d6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23053. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A RAG system can hand you the right answer and cite a source it did not actually use. Models output these unfaithful citations via post-rationalization: they write the answer first and then attach a citation to whatever passage looks close enough. Search agents are now trained with reinforcement learning from verifiable rewards (RLVR), which pays them for getting the answer right. We asked whether that training also teaches them to cite honestly. Improving an existing methodology with a required control, we compared an instruction-tuned model against three RLVR agents trained from it, on four question-answering datasets, using only free-tier Kaggle GPUs. Post-rationalization is everywhere: on Wikipedia-based questions roughly one citation in seven is unfaithful. RLVR does not fix it. The agents post-rationalize at their base model's rate, and one lands slightly worse. Rewarding correct answers buys nothing in citation faithfulness, so faithfulness has to be trained and measured on its own terms.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.23053 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:48:44.969Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).