{"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/optimized-couplings-for-watermarking-large","title":"Optimized Couplings for Watermarking Large Language Models","arxiv_id":"2505.08878","date":"2025-05-13","proceeding":null,"authors":["Dor Tsur","Carol Xuan Long","Claudio Mayrink Verdun","Hsiang Hsu","Haim Permuter","Flavio P. Calmon"],"abstract":"Large-language models (LLMs) are now able to produce text that is, in many cases, seemingly indistinguishable from human-generated content. This has fueled the development of watermarks that imprint a ``signal'' in LLM-generated text with minimal perturbation of an LLM's output. This paper provides an analysis of text watermarking in a one-shot setting. Through the lens of hypothesis testing with side information, we formulate and analyze the fundamental trade-off between watermark detection power and distortion in generated textual quality. We argue that a key component in watermark design is generating a coupling between the side information shared with the watermark detector and a random partition of the LLM vocabulary. Our analysis identifies the optimal coupling and randomization strategy under the worst-case LLM next-token distribution that satisfies a min-entropy constraint. We provide a closed-form expression of the resulting detection rate under the proposed scheme and quantify the cost in a max-min sense. Finally, we provide an array of numerical results, comparing the proposed scheme with the theoretical optimum and existing schemes, in both synthetic data and LLM watermarking. Our code is available at https://github.com/Carol-Long/CC_Watermark","url_abs":"https://arxiv.org/abs/2505.08878v1","url_pdf":"https://arxiv.org/pdf/2505.08878v1.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":"optimized-couplings-for-watermarking-large","repo_url":"https://github.com/carol-long/cc_watermark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"optimized-couplings-for-watermarking-large","repo_url":"https://github.com/dortsur/heavywater_simplexwater","is_official":0,"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=2505.08878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.08878"}},"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/dortsur/heavywater_simplexwater","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/carol-long/cc_watermark","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":2,"samples":[{"code_sha256_prefix":"4e16ec055b8b619e","entry":"tokenize_and_truncate","repo":"carol-long/cc_watermark","repo_kind":"official","path":"LLM_watermarking_exp/watermark/cc_watermark.py","file_url":"https://github.com/carol-long/cc_watermark/blob/HEAD/LLM_watermarking_exp/watermark/cc_watermark.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4e16ec055b8b619e"}},{"code_sha256_prefix":"e145d9988c6ce8ba","entry":"top_p_indices","repo":"carol-long/cc_watermark","repo_kind":"official","path":"LLM_watermarking_exp/watermark/cc_watermark.py","file_url":"https://github.com/carol-long/cc_watermark/blob/HEAD/LLM_watermarking_exp/watermark/cc_watermark.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e145d9988c6ce8ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}