mlsanityData to 7 Oct 2026

C2-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models

arXiv 2602.00004 ↗First posted 19 Nov 2025cs.IR cs.CL cs.DLcited by 0

Not on the map. Why?

Abstract (arXiv)

The attribution technique enhances the credibility of LLMs by adding citations to the generated sentences, enabling users to trace back to the original sources and verify the reliability of the output. However, existing instruction-tuned attributed LLMs often fail to properly interpret the contextual semantics of citation symbols (e.g., [i]) during text generation. This shortcoming arises from their insufficient awareness of the context information surrounding citation markers, which in turn leads to disjointed references and poor integration of retrieved knowledge into the generated content. To address this issue, we propose a novel Contextual-aware Citation generation framework (C2-Cite) that explicitly integrates the semantic relationships between citation markers and their referenced content. Specifically, a contextual citation alignment mechanism is adopted: it first encodes the retrieved document contexts into the symbol representation of citations, then aligns the marker numbers by decoding information from a citation router function. This mechanism enables the transformation of citation markers from generic placeholders into active knowledge pointers that link to the referenced source information. Experimental results on the ALCE benchmark across three datasets validate our framework C2-Cite++: it outperforms the SOTA baseline by an average of 5.8% in citation quality and 17.4% in response correctness. The implementation is publicly available at https://github.com/BAI-LAB/c2cite

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 39 references that are in the map. First posted on arXiv 19 Nov 2025.

Builds on

21 of 39 references.

References · 21

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  2. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  3. 2019ELI5: Long Form Question Answeringcited by 567
  4. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  5. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 395
  6. 2024LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QAcited by 78
  7. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Pathscited by 60
  8. 2024Attribute First, then Generate: Locally-attributable Grounded Text Generationcited by 54
  9. 2023Effective Large Language Model Adaptation for Improved Grounding and Citation Generationcited by 44
  10. 2022QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphscited by 42
  11. 2024Training Language Models to Generate Text with Citations via Fine-grained Rewardscited by 40
  12. 2024Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrievalcited by 26
9 more
  1. 2024Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answeringcited by 25
  2. 2024Making Long-Context Language Models Better Multi-Hop Reasonerscited by 25
  3. 2024Citation-Enhanced Generation for LLM-based Chatbotscited by 24
  4. 2023Towards Verifiable Text Generation with Evolving Memory and Self-Reflectioncited by 21
  5. 2025LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Datacited by 16
  6. 2024Advancing Large Language Model Attribution through Self-Improvingcited by 14
  7. 2023Towards Reliable and Fluent Large Language Models: Incorporating Feedback Learning Loops in QA Systemscited by 10
  8. 2025Lessons from Training Grounded LLMs with Verifiable Rewardscited by 8
  9. 2024Attention with Dependency Parsing Augmentation for Fine-Grained Attributioncited by 5

Built on by

Not cited yet.