Explicit Evidence Grounding via Structured Inline Citation Generation

• URL: http://arxiv.org/abs/2606.07130v1
• Date: Fri, 05 Jun 2026 10:42:10 GMT
• Title: Explicit Evidence Grounding via Structured Inline Citation Generation
• Abstract summary: FullCite is a framework that generates structured inline citations linking each claim to both its source document and supporting evidence.<n>We assess citation quality and faithfulness along three dimensions: document-level correctness, evidence span identification, and claim-citation faithfulness.
• Score: 22.27784103991804
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As AI systems become more widely adopted, the demand for factual and faithful generation grows. Properly attributing information through citations becomes, therefore, crucial. This work introduces FullCite, a framework that, in contrast to most previous works, generates structured inline citations linking each claim to both its source document and supporting evidence. FullCite proposes three strategies to inline citation generation: prompt-based generation, constrained decoding over a citation grammar, and posthoc span alignment. Using three question answering benchmarks, namely, ASQA, BioASQ, and ExpertQA, we assess citation quality and faithfulness along three dimensions: document-level correctness, evidence span identification, and claim-citation faithfulness. Our evaluation shows that while LLMs are generally effective at identifying relevant documents, they struggle to identify the precise supporting spans within them. This gap suggests that achieving faithful attributed QA will require research to place greater emphasis on precise evidence span identification.

Related papers

• Data Citation for Large Language Models: A Challenge [3.18510458102085]
  This paper argues that data citation for large language models is an open challenge.<n>We ask how such models should cite data so that outputs stay verifiable, provenance stays traceable, and credit reaches data creators and curators.
  arXiv  Detail & Related papers  (2026-08-26T11:44:55Z)
• HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research [52.87128503345243]
  We introduce HiEviDR-Bench, a benchmark for evaluating Hierarchical Evidence Aggregation in Deep Research.<n>HiEviDR-Bench represents each instance with an explicit evidence graph that captures evidence selection, cross-source linking, and aggregation.<n>We develop a traceability-oriented evaluation framework with five dimensions: report quality, evidence traceability, citation accuracy, claim verification, and answer correctness.
  arXiv  Detail & Related papers  (2026-07-27T23:50:46Z)
• CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering [27.49652522104852]
  We propose CAGE, a framework that introduces an explicit cognitive attribution map before answer generation.<n>CAGE achieves state-of-the-art performance, demonstrating the effectiveness of attribution-space contraction and map-guided citation generation.
  arXiv  Detail & Related papers  (2026-07-27T10:14:45Z)
• CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era [51.63024682584688]
  Large language models (LLMs) introduce a new risk: fabricated references that appear plausible but correspond to no real publications.<n>We present the first comprehensive benchmark and detection framework for hallucinated citations in scientific writing.<n>Our framework significantly outperforms prior methods in both accuracy and interpretability.
  arXiv  Detail & Related papers  (2026-02-26T19:17:39Z)
• SemanticCite: Citation Verification with AI-Powered Full-Text Analysis and Evidence-Based Reasoning [0.0]
  We introduce SemanticCite, an AI-powered system that verifies citation accuracy through full-text source analysis.<n>Our approach combines multiple retrieval methods with a four-class classification system that captures nuanced claim-source relationships.<n>We contribute a comprehensive dataset of over 1,000 citations with detailed alignments, functional classifications, semantic annotations, and bibliometric metadata.
  arXiv  Detail & Related papers  (2025-11-20T10:05:21Z)
• VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification [107.75781898355562]
  We introduce a novel framework, called VeriCite, designed to rigorously validate supporting evidence and enhance answer attribution.<n>We conduct experiments across five open-source LLMs and four datasets, demonstrating that VeriCite can significantly improve citation quality while maintaining the correctness of the answers.
  arXiv  Detail & Related papers  (2025-10-13T13:38:54Z)
• Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models [44.31597857713689]
  We introduce Active Indexing for the first stage, which creates generalizable, source-anchored bindings.<n>Experiments with Qwen-2.5-7B&3B show that Active Indexing consistently outperforms a Passive Indexing baseline.<n> internal citations complement external ones by making the model more robust to retrieval noise.
  arXiv  Detail & Related papers  (2025-06-21T04:48:05Z)
• ALiiCE: Evaluating Positional Fine-grained Citation Generation [54.19617927314975]
  We propose ALiiCE, the first automatic evaluation framework for fine-grained citation generation. Our framework first parses the sentence claim into atomic claims via dependency analysis and then calculates citation quality at the atomic claim level. We evaluate the positional fine-grained citation generation performance of several Large Language Models on two long-form QA datasets.
  arXiv  Detail & Related papers  (2024-06-19T09:16:14Z)
• Verifiable Generation with Subsentence-Level Fine-Grained Citations [13.931548733211436]
  Verifiable generation requires large language models to cite source documents supporting their outputs. Previous work mainly targets the generation of sentence-level citations, lacking specificity about which parts of a sentence are backed by the cited sources. This work studies verifiable generation with subsentence-level fine-grained citations for more precise location of generated content supported by the cited sources.
  arXiv  Detail & Related papers  (2024-06-10T09:32:37Z)
• CiteBench: A benchmark for Scientific Citation Text Generation [69.37571393032026]
  CiteBench is a benchmark for citation text generation. We make the code for CiteBench publicly available at https://github.com/UKPLab/citebench.
  arXiv  Detail & Related papers  (2022-12-19T16:10:56Z)
• GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
  We propose GERE, the first system that retrieves evidences in a generative fashion. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-12T03:49:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.