Faithful by Construction: Claim-Anchored Attribution for Multi-Document Summarization

• URL: http://arxiv.org/abs/2606.23989v2
• Date: Wed, 01 Jul 2026 00:27:13 GMT
• Title: Faithful by Construction: Claim-Anchored Attribution for Multi-Document Summarization
• Abstract summary: Claim-Anchored Multi-document Summarization framework ( CAMS)<n>Claim-Anchored Multi-document Summarization framework ( CAMS)
• Score: 1.1168121941015015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end large language models (LLMs) produce fluent multi-document summaries but remain prone to hallucination, and the attributions they offer are typically coarse (whole documents or passages) and generated post hoc, leaving each summary statement hard to verify. We revisit the modular Extract--Select--Rewrite paradigm and recast its intermediate representation as the unit of attribution. We present CAMS, a Claim-Anchored Multi-document Summarization framework that (i) extracts atomic claims with token-level provenance from every source document, (ii) clusters equivalent claims across documents while flagging inter-source conflicts, (iii) selects a support-aware and salient subset, and (iv) rewrites the selection into a summary in which every sentence is anchored to a support-checked claim that links back to one or more source spans. Because content is localized before it is realized, the pipeline is attribution-oriented by construction and faithfulness-oriented by construction: it structurally preserves fine-grained, multi-source traceability while using support-aware selection, constrained rewriting, and verification to encourage, rather than guarantee, factual faithfulness. We evaluate quality, faithfulness, and localization on MultiNews, analyze conflict handling on DiverseSumm, and test zero-shot transfer on WCEP, using a two-regime protocol that separates reference-free citation quality from gold-aligned localization accuracy, and we add an evaluator-decoupled audit that tests citation precision with a support model never used for selection or verification. CAMS matches strong end-to-end and span-attribution baselines on summary quality while substantially improving faithfulness and citation precision, lifting multi-source attribution accuracy by roughly two-thirds, and exposing a controllable faithfulness--coverage trade-off that end-to-end models leave implicit.

Related papers

• Decomposed Entailment for Factuality Checking and Hallucination Detection [0.3602004729891047]
  HallDetect is a lightweight, reference-free, and black-box framework for hallucination detection.<n> generated content is decomposed into atomic claims, verified by a compact encoder-based entailment model.<n>Under a controlled protocol, all methods share the same 4-bit quantized backbones and consumer-grade hardware budget.
  arXiv  Detail & Related papers  (2026-08-06T09:52:09Z)
• Cross-platform epistemic verification for improving factual reliability in AI-generated news summarization [0.0]
  This study proposes Multi-source Evidence Consen- sus Verification (MECV) for AI-generated news summariza- tion.<n>Instead of depending on a single retrieval channel, MECV aggregates evidence from multiple heterogeneous sources, including the source document, Wikipedia, and open-web retrieval.
  arXiv  Detail & Related papers  (2026-08-05T18:01:24Z)
• 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)
• Dual-Confidence Contrastive Decoding for Retrieval-Augmented Generation [18.633632165243423]
  We study the complementary problem of intra-context conflict in multi-document RAG.<n>We propose Dual-Confidence Contrastive Decoding (DCCD) as a training-free decoding method.<n>DCCD achieves the best average performance among full-context and contrastive decoding baselines.
  arXiv  Detail & Related papers  (2026-07-01T07:55:21Z)
• Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding [64.98167175790817]
  We propose ConSUM that reranks candidate summaries by considering two factors: consistency to the source document and consensus among the other candidates.<n>Our system is competitive with existing methods, with human evaluations confirming that its generated summaries are preferred over those from other systems.
  arXiv  Detail & Related papers  (2026-05-28T04:14:43Z)
• CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents [6.134883925217888]
  We propose CHOP, a framework that iteratively evaluates chunk relevance with Large Language Models (LLMs)<n>CHOP integrates two key components: the CNM-Extractor, which generates compact per-chunk signatures capturing categories, key nouns, and model names, and the Continuity Decision Module, which preserves contextual coherence.<n> Experiments on benchmark datasets show that CHOP alleviates retrieval confusion and provides a scalable approach for building high-quality knowledge bases.
  arXiv  Detail & Related papers  (2026-04-17T08:05:17Z)
• MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering [51.19392014547221]
  Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures.<n>Current approaches rely on query-agnostic document representations that overlook salient content.<n>We propose the Multimodal Adaptive Retrieval-Augmented (MARA) framework, which introduces query-adaptive generation.
  arXiv  Detail & Related papers  (2026-02-01T12:27:40Z)
• MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents [37.98503734345155]
  We introduce MMDeepResearch-Bench (MMDR-Bench), a benchmark of 140 expert-crafted tasks across 21 domains.<n>Compared to prior setups, MMDR-Bench emphasizes report-style synthesis with explicit evidence use.<n>We propose a unified, interpretable evaluation pipeline: Formula-LLM Adaptive Evaluation (FLAE) for report quality, Trustworthy Retrieval-Aligned Citation Evaluation (TRACE) for citation-grounded evidence alignment, and Multimodal Support-Aligned Integrity Check (MOSAIC) for text-visual integrity.
  arXiv  Detail & Related papers  (2026-01-18T10:41:33Z)
• 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)
• Towards Knowledge-Aware Document Systems: Modeling Semantic Coverage Relations via Answerability Detection [40.12543056558646]
  We introduce a novel framework for modelling Semantic Coverage Relations (SCR), which classifies document pairs based on how their informational content aligns.<n>We define three core relation types: equivalence, inclusion, and semantic overlap.<n>We use a question answering (QA)-based approach, using the answerability of shared questions across documents as an indicator of semantic coverage.
  arXiv  Detail & Related papers  (2025-09-10T06:00:01Z)
• Unstructured Evidence Attribution for Long Context Query Focused Summarization [53.08341620504465]
  We propose to extract unstructured (i.e., spans of any length) evidence in order to acquire more relevant and consistent evidence than in the fixed granularity case.<n>We show how existing systems struggle to copy and properly cite unstructured evidence, which also tends to be "lost-in-the-middle"
  arXiv  Detail & Related papers  (2025-02-20T09:57:42Z)
• 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)
• 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.