{"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/simmark-a-robust-sentence-level-similarity","title":"SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models","arxiv_id":"2502.02787","date":"2025-02-05","proceeding":null,"authors":["Amirhossein Dabiriaghdam","Lele Wang"],"abstract":"The rapid proliferation of large language models (LLMs) has created an urgent need for reliable methods to detect whether a text is generated by such models. In this paper, we propose SimMark, a posthoc watermarking algorithm that makes LLMs' outputs traceable without requiring access to the model's internal logits, enabling compatibility with a wide range of LLMs, including API-only models. By leveraging the similarity of semantic sentence embeddings and rejection sampling to impose detectable statistical patterns imperceptible to humans, and employing a soft counting mechanism, SimMark achieves robustness against paraphrasing attacks. Experimental results demonstrate that SimMark sets a new benchmark for robust watermarking of LLM-generated content, surpassing prior sentence-level watermarking techniques in robustness, sampling efficiency, and applicability across diverse domains, all while preserving the text quality.","url_abs":"https://arxiv.org/abs/2502.02787v1","url_pdf":"https://arxiv.org/pdf/2502.02787v1.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":"simmark-a-robust-sentence-level-similarity","repo_url":"https://github.com/DabiriAghdam/SimMark","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.02787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02787"}},"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/DabiriAghdam/SimMark","reach":null}],"summary":{"ran_draft_wrong":1,"ran_fixture":2},"by_repo_kind":{"official":{"samples":3,"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":"bca3b5ce3d3ba0f4","entry":"detect","repo":"DabiriAghdam/SimMark","repo_kind":"official","path":"detection.py","file_url":"https://github.com/DabiriAghdam/SimMark/blob/HEAD/detection.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bca3b5ce3d3ba0f4"}},{"code_sha256_prefix":"d478d84b3b451a99","entry":"distance_to_intervals","repo":"DabiriAghdam/SimMark","repo_kind":"official","path":"detection.py","file_url":"https://github.com/DabiriAghdam/SimMark/blob/HEAD/detection.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d478d84b3b451a99"}},{"code_sha256_prefix":"edda57f11af4db0d","entry":"in_interval","repo":"DabiriAghdam/SimMark","repo_kind":"official","path":"detection.py","file_url":"https://github.com/DabiriAghdam/SimMark/blob/HEAD/detection.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"edda57f11af4db0d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}