{"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/morphmark-flexible-adaptive-watermarking-for","title":"MorphMark: Flexible Adaptive Watermarking for Large Language Models","arxiv_id":"2505.11541","date":"2025-05-14","proceeding":null,"authors":["Zongqi Wang","Tianle Gu","Baoyuan Wu","Yujiu Yang"],"abstract":"Watermarking by altering token sampling probabilities based on red-green list is a promising method for tracing the origin of text generated by large language models (LLMs). However, existing watermark methods often struggle with a fundamental dilemma: improving watermark effectiveness (the detectability of the watermark) often comes at the cost of reduced text quality. This trade-off limits their practical application. To address this challenge, we first formalize the problem within a multi-objective trade-off analysis framework. Within this framework, we identify a key factor that influences the dilemma. Unlike existing methods, where watermark strength is typically treated as a fixed hyperparameter, our theoretical insights lead to the development of MorphMarka method that adaptively adjusts the watermark strength in response to changes in the identified factor, thereby achieving an effective resolution of the dilemma. In addition, MorphMark also prioritizes flexibility since it is a model-agnostic and model-free watermark method, thereby offering a practical solution for real-world deployment, particularly in light of the rapid evolution of AI models. Extensive experiments demonstrate that MorphMark achieves a superior resolution of the effectiveness-quality dilemma, while also offering greater flexibility and time and space efficiency.","url_abs":"https://arxiv.org/abs/2505.11541v2","url_pdf":"https://arxiv.org/pdf/2505.11541v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"morphmark-flexible-adaptive-watermarking-for","repo_url":"https://github.com/thu-bpm/markllm","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.11541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.11541"}},"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/thu-bpm/markllm","reach":null}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":"a81fb7c8ec5d72f5","entry":"BaseWatermark","repo":"thu-bpm/markllm","repo_kind":"official","path":"watermark/morphmark/morphmark.py","file_url":"https://github.com/thu-bpm/markllm/blob/HEAD/watermark/morphmark/morphmark.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a81fb7c8ec5d72f5"}},{"code_sha256_prefix":"71ba009328036e00","entry":"MorphMarkConfig","repo":"thu-bpm/markllm","repo_kind":"official","path":"watermark/morphmark/morphmark.py","file_url":"https://github.com/thu-bpm/markllm/blob/HEAD/watermark/morphmark/morphmark.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"71ba009328036e00"}},{"code_sha256_prefix":"cc781703afcc6ba9","entry":"MorphMarkLogitsProcessor","repo":"thu-bpm/markllm","repo_kind":"official","path":"watermark/morphmark/morphmark.py","file_url":"https://github.com/thu-bpm/markllm/blob/HEAD/watermark/morphmark/morphmark.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc781703afcc6ba9"}},{"code_sha256_prefix":"8dc8fc456112ecd8","entry":"BaseConfig","repo":"thu-bpm/markllm","repo_kind":"official","path":"watermark/morphmark/morphmark.py","file_url":"https://github.com/thu-bpm/markllm/blob/HEAD/watermark/morphmark/morphmark.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8dc8fc456112ecd8"}},{"code_sha256_prefix":"0db293ccd5882577","entry":"MorphMark","repo":"thu-bpm/markllm","repo_kind":"official","path":"watermark/morphmark/morphmark.py","file_url":"https://github.com/thu-bpm/markllm/blob/HEAD/watermark/morphmark/morphmark.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0db293ccd5882577"}},{"code_sha256_prefix":"60742f92ea6ca774","entry":"MorphMarkUtils","repo":"thu-bpm/markllm","repo_kind":"official","path":"watermark/morphmark/morphmark.py","file_url":"https://github.com/thu-bpm/markllm/blob/HEAD/watermark/morphmark/morphmark.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"60742f92ea6ca774"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}