Lune

ACL Findings2025

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

Jiajun Shen, Tong Zhou, Yubo Chen, Delai Qiu, Shengping Liu, Kang Liu, Jun Zhao

Abstract

While hallucinations of large language models could been alleviated through retrievalaugmented 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 crossscenario 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation cites Enabling Large Language Models to Generate Text with Citations
  • FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation cites Evaluating Verifiability in Generative Search Engines
  • Enabling Large Language Models to Generate Text with Citations cites Evaluating Verifiability in Generative Search Engines
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on24

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations
  3. FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text GenerationSewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis et al.EMNLP 2023 · 225 citations
  4. Enabling Large Language Models to Generate Text with CitationsTianyu Gao, Howard Yen, Jiatong Yu, Danqi ChenEMNLP 2023 · 152 citations
  5. Evaluating Verifiability in Generative Search EnginesNelson F. Liu, Tianyi Zhang, Percy LiangEMNLP Findings 2023 · 143 citations

Related papers

  1. Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to RefuseMaojia Song, Shang Hong Sim, Rishabh Bhardwaj, Hai Leong Chieu et al.ICLR 2025
  2. Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement LearningZongmeng Zhang, Yufeng Shi, Jinhua Zhu, Wengang Zhou et al.ICML 2024 · 3 citations
  3. Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented GenerationJirui Qi, Gabriele Sarti, Raquel Fernández, Arianna BisazzaEMNLP 2024 · 6 citations
  4. CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented ValidationYee Man Choi, Xuehang Guo, Yi R. Fung, Qingyun WangACL 2026 · 7 citations
  5. FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"Yifei Ming, Senthil Purushwalkam, Shrey Pandit, Zixuan Ke et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines