# Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation

arXiv: https://arxiv.org/abs/2504.14856 · HTML: https://mlsanity.com/paper/2504.14856/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 37 of its 47 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 30 of 37)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [ASQA: Factoid Questions Meet Long-Form Answers](https://mlsanity.com/paper/2204.06092/) (2022)
- [Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification](https://mlsanity.com/paper/2403.04696/) (2024)
- [Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.12941/) (2024)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [ContextCite: Attributing Model Generation to Context](https://mlsanity.com/paper/2409.00729/) (2024)
- [Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2402.14409/) (2024)
- [FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"](https://mlsanity.com/paper/2410.03727/) (2024)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks](https://mlsanity.com/paper/2304.14732/) (2023)
- [Effective Large Language Model Adaptation for Improved Grounding and Citation Generation](https://mlsanity.com/paper/2311.09533/) (2023)
- [When to Trust LLMs: Aligning Confidence with Response Quality](https://mlsanity.com/paper/2404.17287/) (2024)
- [Training Language Models to Generate Text with Citations via Fine-grained Rewards](https://mlsanity.com/paper/2402.04315/) (2024)
- [Learning to Plan and Generate Text with Citations](https://mlsanity.com/paper/2404.03381/) (2024)
- [Retrieving Complex Tables with Multi-Granular Graph Representation Learning](https://mlsanity.com/paper/2105.01736/) (2021)
- [Improving Attributed Text Generation of Large Language Models via Preference Learning](https://mlsanity.com/paper/2403.18381/) (2024)
- [Controllable Context Sensitivity and the Knob Behind It](https://mlsanity.com/paper/2411.07404/) (2024)
- [Towards Verifiable Text Generation with Evolving Memory and Self-Reflection](https://mlsanity.com/paper/2312.09075/) (2023)
- [Citations and Trust in LLM Generated Responses](https://mlsanity.com/paper/2501.01303/) (2025)
- [Towards Fine-Grained Citation Evaluation in Generated Text: A Comparative Analysis of Faithfulness Metrics](https://mlsanity.com/paper/2406.15264/) (2024)
- [ALiiCE: Evaluating Positional Fine-grained Citation Generation](https://mlsanity.com/paper/2406.13375/) (2024)
- [Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations](https://mlsanity.com/paper/2410.04241/) (2024)
- [Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responses](https://mlsanity.com/paper/2410.22349/) (2024)
- [Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data](https://mlsanity.com/paper/2404.03862/) (2024)

## Built on by (most cited first, 4 of 4)

- [Whose Facts Win? LLM Source Preferences under Knowledge Conflicts](https://mlsanity.com/paper/2601.03746/) (2026)
- [In-Context Credit Assignment via the Core](https://mlsanity.com/paper/2605.06920/) (2026)
- [CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering](https://mlsanity.com/paper/2607.24236/) (2026)
- [CLINB: A Climate Intelligence Benchmark for Foundational Models](https://mlsanity.com/paper/2511.11597/) (2025)

## Abstract (arXiv)

While hallucinations of large language models could been alleviated through retrieval-augmented generation and citation generation, how the model utilizes internal knowledge is still opaque, and the trustworthiness of its generated answers remains questionable. In this work, we introduce Context-Prior Augmented Citation Generation task, requiring models to generate citations considering both external and internal knowledge while providing trustworthy references, with 5 evaluation metrics focusing on 3 aspects: answer helpfulness, citation faithfulness, and trustworthiness. We introduce RAEL, the paradigm for our task, and also design INTRALIGN, an integrated method containing customary data generation and an alignment algorithm. Our experimental results show that our method achieves a better cross-scenario performance with regard to other baselines. Our extended experiments further reveal that retrieval quality, question types, and model knowledge have considerable influence on the trustworthiness in citation generation.