mlsanityData to 7 Oct 2026

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

arXiv 2609.23053 ↗First posted 19 Sep 2026cs.CL cs.IRcited by 0

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory also fits: RAG robustness and adaptive retrieval

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 5 of its 10 references that are in the map. First posted on arXiv 19 Sep 2026.

Builds on

5 of 10 references.

References · 5

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  3. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  4. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  5. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 272

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation
  2. 2026MCite-RL: Towards Reliable Multimodal RAG via Citation-enhanced Agentic Reinforcement Learning
  3. 2024Correctness is not Faithfulness in RAG Attributions
  4. 2025VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification
  5. 2025Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning
  6. 2026How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
  7. 2026CITECHOICE: A Causal Audit of How Document Presentation Redistributes Citation Credit in Agentic Search
  8. 2026Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards