{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/writingbench-a-comprehensive-benchmark-for","title":"WritingBench: A Comprehensive Benchmark for Generative Writing","arxiv_id":"2503.05244","date":"2025-03-07","proceeding":null,"authors":["Yuning Wu","Jiahao Mei","Ming Yan","Chenliang Li","Shaopeng Lai","Yuran Ren","Zijia Wang","Ji Zhang","Mengyue Wu","Qin Jin","Fei Huang"],"abstract":"Recent advancements in large language models (LLMs) have significantly enhanced text generation capabilities, yet evaluating their performance in generative writing remains a challenge. Existing benchmarks primarily focus on generic text generation or limited in writing tasks, failing to capture the diverse requirements of high-quality written contents across various domains. To bridge this gap, we present WritingBench, a comprehensive benchmark designed to evaluate LLMs across 6 core writing domains and 100 subdomains, encompassing creative, persuasive, informative, and technical writing. We further propose a query-dependent evaluation framework that empowers LLMs to dynamically generate instance-specific assessment criteria. This framework is complemented by a fine-tuned critic model for criteria-aware scoring, enabling evaluations in style, format and length. The framework's validity is further demonstrated by its data curation capability, which enables 7B-parameter models to approach state-of-the-art (SOTA) performance. We open-source the benchmark, along with evaluation tools and modular framework components, to advance the development of LLMs in writing.","url_abs":"https://arxiv.org/abs/2503.05244v2","url_pdf":"https://arxiv.org/pdf/2503.05244v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"writingbench-a-comprehensive-benchmark-for","repo_url":"https://github.com/X-PLUG/WritingBench","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.05244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.05244"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/X-PLUG/WritingBench","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1321e6d2e53e2bb3","entry":"load_file","repo":"X-PLUG/WritingBench","repo_kind":"official","path":"generate_response.py","file_url":"https://github.com/X-PLUG/WritingBench/blob/HEAD/generate_response.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1321e6d2e53e2bb3"}},{"code_sha256_prefix":"eabc5f8b3c9962b1","entry":"process_gen_field","repo":"X-PLUG/WritingBench","repo_kind":"official","path":"evaluate_benchmark.py","file_url":"https://github.com/X-PLUG/WritingBench/blob/HEAD/evaluate_benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eabc5f8b3c9962b1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}