Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation

arXiv:2604.01432 · cs.CL · Submitted 2026-04-01 · Read on arXiv

cs.CL

Submitted: 2026-04-01

Updated: 2026-09-20

Code: https://github.com/JHU-CLSP/citation-granularity

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verification — 15× in this paper · explained in 2 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Alignment — 11× in this paper · explained in 1 episode
• Accuracy — 8× in this paper · explained in 1 episode
• F1 Score — 7× in this paper · explained in 3 episodes
• LLM judge — 4× in this paper · explained in 2 episodes
• Structural Constraints — 4× in this paper · explained in 2 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• RAG — 3× in this paper · explained in 3 episodes
• Verifiability — 3× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Granularity Mismatch — 2× in this paper · explained in 2 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding Large Language Model — 1× in this paper
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Semantic Gap — 1× in this paper · explained in 2 episodes
• Systematic Bias — 1× in this paper · explained in 3 episodes

Sources

• Citation-Grounded Code Comprehension: Preventing LLM Hallucination Through Hybrid Retrieval and Graph-Augmented Context
• Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find
• Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models
• Long-context LLMs Struggle with Long In-context Learning
• A Comprehensive Survey on Long Context Language Modeling
• Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation
• Lost in the Middle: How Language Models Use Long Contexts
• A Survey of Scaling in Large Language Model Reasoning
• The Llama 3 Herd of Models
• Teaching language models to support answers with verified quotes
• WebGPT: Browser-assisted question-answering with human feedback
• gpt-oss-120b & gpt-oss-20b Model Card
• Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models
• LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
• More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG
• LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
• Finding the Minimal Parameter Budget for Implicit Reasoning: A Data Complexity Driven Scaling Law for Language Models
• Retrieval Head Mechanistically Explains Long-Context Factuality
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering