# Correctness is not Faithfulness in RAG Attributions

arXiv: https://arxiv.org/abs/2412.18004 · HTML: https://mlsanity.com/paper/2412.18004/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 59 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Builds on (most cited first, 26 of 26)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI](https://mlsanity.com/paper/2010.07487/) (2020)
- [Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models](https://mlsanity.com/paper/2212.08037/) (2022)
- [Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models](https://mlsanity.com/paper/2402.04614/) (2024)
- [Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations](https://mlsanity.com/paper/2307.08678/) (2023)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution](https://mlsanity.com/paper/2307.16883/) (2023)
- [Attribute First, then Generate: Locally-attributable Grounded Text Generation](https://mlsanity.com/paper/2403.17104/) (2024)
- [PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions](https://mlsanity.com/paper/2305.14908/) (2023)
- [Resolving Knowledge Conflicts in Large Language Models](https://mlsanity.com/paper/2310.00935/) (2023)
- [Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods](https://mlsanity.com/paper/1910.02065/) (2019)
- [Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI](https://mlsanity.com/paper/2311.01463/) (2023)
- [Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.13663/) (2024)
- [Evaluation of RAG Metrics for Question Answering in the Telecom Domain](https://mlsanity.com/paper/2407.12873/) (2024)
- [Towards Fine-Grained Citation Evaluation in Generated Text: A Comparative Analysis of Faithfulness Metrics](https://mlsanity.com/paper/2406.15264/) (2024)
- [Robust Conversational AI with Grounded Text Generation](https://mlsanity.com/paper/2009.03457/) (2020)

## Built on by (most cited first, 18 of 18)

- [Deep Research: A Survey of Autonomous Research Agents](https://mlsanity.com/paper/2508.12752/) (2025)
- [Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents](https://mlsanity.com/paper/2604.03173/) (2026)
- [EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models](https://mlsanity.com/paper/2603.19532/) (2026)
- [LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger](https://mlsanity.com/paper/2607.28374/) (2026)
- [CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.05467/) (2026)
- [Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV](https://mlsanity.com/paper/2607.23693/) (2026)
- [Advancing ESG Intelligence: An Expert-level Agent and Comprehensive Benchmark for Sustainable Finance](https://mlsanity.com/paper/2601.08676/) (2026)
- [H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations](https://mlsanity.com/paper/2605.00631/) (2026)
- [Tracing Facts or just Copies? A critical investigation of the Competitions of Mechanisms in Large Language Models](https://mlsanity.com/paper/2507.11809/) (2025)
- [Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokens](https://mlsanity.com/paper/2508.08942/) (2025)
- [RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners](https://mlsanity.com/paper/2605.00199/) (2026)
- [Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG](https://mlsanity.com/paper/2605.15109/) (2026)
- [Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA](https://mlsanity.com/paper/2606.03728/) (2026)
- [Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibration](https://mlsanity.com/paper/2606.21595/) (2026)
- [Evaluating and Guarding Citation Faithfulness in Agentic Scientific Synthesis](https://mlsanity.com/paper/2607.20527/) (2026)
- [VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations](https://mlsanity.com/paper/2608.03675/) (2026)
- [Do LLMs Understand Context? A Knowledge Graph-Based Evaluation Framework](https://mlsanity.com/paper/2609.30484/) (2026)
- [Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memory](https://mlsanity.com/paper/2609.33822/) (2026)

## Abstract (arXiv)

Retrieving relevant context is a common approach to reduce hallucinations and enhance answer reliability. Explicitly citing source documents allows users to verify generated responses and increases trust. Prior work largely evaluates citation correctness - whether cited documents support the corresponding statements. But citation correctness alone is insufficient. To establish trust in attributed answers, we must examine both citation correctness and citation faithfulness. In this work, we first disentangle the notions of citation correctness and faithfulness, which have been applied inconsistently in previous studies. Faithfulness ensures that the model's reliance on cited documents is genuine, reflecting actual reference use rather than superficial alignment with prior beliefs, which we call post-rationalization. We design an experiment that reveals the prevalent issue of post-rationalization, which undermines reliable attribution and may result in misplaced trust. Our findings suggest that current attributed answers often lack citation faithfulness (up to 57 percent of the citations), highlighting the need to evaluate correctness and faithfulness for trustworthy attribution in language models.