{"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/a-robust-semantics-based-watermark-for-large","title":"A Robust Semantics-based Watermark for Large Language Model against Paraphrasing","arxiv_id":"2311.08721","date":"2023-11-15","proceeding":null,"authors":["Jie Ren","Han Xu","Yiding Liu","Yingqian Cui","Shuaiqiang Wang","Dawei Yin","Jiliang Tang"],"abstract":"Large language models (LLMs) have show great ability in various natural language tasks. However, there are concerns that LLMs are possible to be used improperly or even illegally. To prevent the malicious usage of LLMs, detecting LLM-generated text becomes crucial in the deployment of LLM applications. Watermarking is an effective strategy to detect the LLM-generated content by encoding a pre-defined secret watermark to facilitate the detection process. However, the majority of existing watermark methods leverage the simple hashes of precedent tokens to partition vocabulary. Such watermark can be easily eliminated by paraphrase and correspondingly the detection effectiveness will be greatly compromised. Thus, to enhance the robustness against paraphrase, we propose a semantics-based watermark framework SemaMark. It leverages the semantics as an alternative to simple hashes of tokens since the paraphrase will likely preserve the semantic meaning of the sentences. Comprehensive experiments are conducted to demonstrate the effectiveness and robustness of SemaMark under different paraphrases.","url_abs":"https://arxiv.org/abs/2311.08721v2","url_pdf":"https://arxiv.org/pdf/2311.08721v2.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":"a-robust-semantics-based-watermark-for-large","repo_url":"https://github.com/renjie3/semamark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.08721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08721"}},"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/renjie3/semamark","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"3e107246e54539b5","entry":"additive_prf","repo":"renjie3/semamark","repo_kind":"official","path":"alternative_prf_schemes.py","file_url":"https://github.com/renjie3/semamark/blob/HEAD/alternative_prf_schemes.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e107246e54539b5"}},{"code_sha256_prefix":"91467442d43e757d","entry":"cosine_similarity","repo":"renjie3/semamark","repo_kind":"official","path":"emb_nering_sim.py","file_url":"https://github.com/renjie3/semamark/blob/HEAD/emb_nering_sim.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91467442d43e757d"}},{"code_sha256_prefix":"ab84746bf94016d2","entry":"multiplicative_prf","repo":"renjie3/semamark","repo_kind":"official","path":"alternative_prf_schemes.py","file_url":"https://github.com/renjie3/semamark/blob/HEAD/alternative_prf_schemes.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab84746bf94016d2"}},{"code_sha256_prefix":"e7a03d0cb73618fd","entry":"seeding_scheme_lookup","repo":"renjie3/semamark","repo_kind":"official","path":"alternative_prf_schemes.py","file_url":"https://github.com/renjie3/semamark/blob/HEAD/alternative_prf_schemes.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e7a03d0cb73618fd"}},{"code_sha256_prefix":"ea5605d2bfcf0722","entry":"get_vocab_embeddings","repo":"renjie3/semamark","repo_kind":"official","path":"get_emb.py","file_url":"https://github.com/renjie3/semamark/blob/HEAD/get_emb.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea5605d2bfcf0722"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}