# CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering

arXiv: https://arxiv.org/abs/2607.24236 · HTML: https://mlsanity.com/paper/2607.24236/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Builds on (most cited first, 25 of 25)

- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [ASQA: Factoid Questions Meet Long-Form Answers](https://mlsanity.com/paper/2204.06092/) (2022)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [ExpertQA: Expert-Curated Questions and Attributed Answers](https://mlsanity.com/paper/2309.07852/) (2023)
- [LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA](https://mlsanity.com/paper/2409.02897/) (2024)
- [Large Language Models and Knowledge Graphs: Opportunities and Challenges](https://mlsanity.com/paper/2308.06374/) (2023)
- [Attribute First, then Generate: Locally-attributable Grounded Text Generation](https://mlsanity.com/paper/2403.17104/) (2024)
- [Effective Large Language Model Adaptation for Improved Grounding and Citation Generation](https://mlsanity.com/paper/2311.09533/) (2023)
- [Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse](https://mlsanity.com/paper/2409.11242/) (2024)
- [Source-Aware Training Enables Knowledge Attribution in Language Models](https://mlsanity.com/paper/2404.01019/) (2024)
- [Improving Attributed Text Generation of Large Language Models via Preference Learning](https://mlsanity.com/paper/2403.18381/) (2024)
- [Atomic Fact Decomposition Helps Attributed Question Answering](https://mlsanity.com/paper/2410.16708/) (2024)
- [A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects](https://mlsanity.com/paper/2308.02457/) (2023)
- [Advancing Large Language Model Attribution through Self-Improving](https://mlsanity.com/paper/2410.13298/) (2024)
- [Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards](https://mlsanity.com/paper/2601.06021/) (2026)
- [Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG](https://mlsanity.com/paper/2605.28044/) (2026)
- [LAQuer: Localized Attribution Queries in Content-grounded Generation](https://mlsanity.com/paper/2506.01187/) (2025)
- [Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs](https://mlsanity.com/paper/2410.20321/) (2024)
- [Lessons from Training Grounded LLMs with Verifiable Rewards](https://mlsanity.com/paper/2506.15522/) (2025)
- [Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling](https://mlsanity.com/paper/2412.14860/) (2024)
- [Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation](https://mlsanity.com/paper/2504.14856/) (2025)
- [Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities](https://mlsanity.com/paper/2508.01290/) (2025)

## Built on by (most cited first, 1 of 1)

- [Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning](https://mlsanity.com/paper/2608.03123/) (2026)

## Abstract (arXiv)

Long-form question answering increasingly relies on retrieved evidence to make LLM outputs verifiable, with inline citations tracing claims to source documents. However, existing systems often attach citations that are topically related but insufficient to support their claims. We identify attribution ambiguity as a structural challenge: end-to-end generation must implicitly resolve combinatorial claim--document assignments, obscuring evidential boundaries and increasing the risk of evidence-boundary overrun, where claims exceed cited support. To address this challenge, we propose CAGE (Cognitive Attribution Graphs for Citation Generation), a two-stage framework that introduces an explicit cognitive attribution map before answer generation. CAGE first trains a plug-and-play Cognitive Map Induction Model to construct answer-centered support subgraphs, aligning each semantic answer unit with supporting documents through explicit relations. A Structured Citation Reasoning Model then realizes these units as sentence-level claims with map-aligned citations. Experiments on ASQA, ELI5, and ExpertQA show that CAGE achieves state-of-the-art performance, demonstrating the effectiveness of attribution-space contraction and map-guided citation generation.