{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.01936", "kind": "paper", "url": "https://arxiv.org/abs/2606.01936"}], "authors": ["Shihao Rao", "Liang Li", "Jiapeng Liu", "Tong Lin", "Bing Li", "Xiyan Gao", "Peng Fu", "Jing Huang", "Can Ma"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.01936", "source_url": "https://arxiv.org/abs/2606.01936"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "DocFormBench evaluates content-aware document formatting for LLMs and multimodal models, using accuracy and efficiency metrics, with a workflow method DocFormFlow for target localization and modification."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.01936", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.01936", "title": "DocFormBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Chinese Academy of Sciences", "Institute of Information Engineering", "University of Chinese Academy of Sciences"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.01936", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.01936", "source_url": "https://openalex.org/W7163218947"}, "key": "claire-radar:2606.01936", "modality": null, "name": "DocFormBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_docformbench_158426e5", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "d5e37cd5ab5476b97c50104347a62e7f93d3b51451660e14f7c5a1dfaabe536c", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.01936"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.01936", "source_url": "https://arxiv.org/abs/2606.01936"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-01936", "source": "claire_radar", "source_benchmark_id": "2606.01936", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.01936", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "0920d8cee2885bea75469eb16ce61d085ba8678b37b7ce072f88a79cc65ce840", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "DocFormBench evaluates content-aware document formatting for LLMs and multimodal models, using accuracy and efficiency metrics, with a workflow method DocFormFlow for target localization and modification.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence"], "snippet": "This content-aware setting remains challenging and underexplored, primarily due to the lack of dedicated evaluation datasets.To enable evaluation in realistic content-aware scenarios, we introduce DocFormBench, a benchmark that extends Text-to-Format evaluation to diverse formatting requirements, along with metrics for both accuracy and efficiency.To mitigate redundant document reading in existing methods during formatting, we propose DocFormFlow, a workflow formatting method that decouples targ"}, "familyId": "bmf_7b27e2f9f67b", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_docformbench_158426e5", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.01936", "paper": "https://arxiv.org/abs/2606.01936", "pdf": "https://arxiv.org/pdf/2606.01936", "project": null, "report": "https://arxiv.org/abs/2606.01936"}, "metrics": [], "motivation": "Recent advances in large language models (LLMs) have opened up new possibilities for automated document formatting.", "name": "DocFormBench", "oneLine": "DocFormBench evaluates content-aware document formatting for LLMs and multimodal models, using accuracy and efficiency metrics, with a workflow method DocFormFlow for target localization and modification.", "paperTitle": "What to Format and How: A Benchmark and Workflow Approach for Document Formatting", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.01936", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-01", "source": {"authors": ["Shihao Rao", "Liang Li", "Jiapeng Liu", "Tong Lin", "Bing Li", "Xiyan Gao", "Peng Fu", "Jing Huang", "Can Ma"], "categories": ["cs.CL"], "id": "2606.01936", "title": "What to Format and How: A Benchmark and Workflow Approach for Document Formatting", "type": "arxiv", "url": "https://arxiv.org/abs/2606.01936"}, "sourceUpdatedAt": "2026-06-01T09:02:33Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Existing formatting benchmarks lack content-aware evaluation, leaving a gap in assessing target identification. This benchmark addresses that by providing diverse formatting requirements and metrics for accuracy and efficiency, enabling practical comparison of formatting models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
