{"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/cave-controllable-authorship-verification","title":"CAVE: Controllable Authorship Verification Explanations","arxiv_id":"2406.16672","date":"2024-06-24","proceeding":null,"authors":["Sahana Ramnath","Kartik Pandey","Elizabeth Boschee","Xiang Ren"],"abstract":"Authorship Verification (AV) (do two documents have the same author?) is essential in many sensitive real-life applications. AV is often used in proprietary domains that require a private, offline model, making SOTA online models like ChatGPT undesirable. Current offline models however have lower downstream utility due to low accuracy/scalability (eg: traditional stylometry AV systems) and lack of accessible post-hoc explanations. In this work, we take the first step to address the above challenges with our trained, offline Llama-3-8B model CAVE (Controllable Authorship Verification Explanations): CAVE generates free-text AV explanations that are controlled to be (1) structured (can be decomposed into sub-explanations in terms of relevant linguistic features), and (2) easily verified for explanation-label consistency (via intermediate labels in sub-explanations). We first engineer a prompt that can generate silver training data from a SOTA teacher model in the desired CAVE output format. We then filter and distill this data into a pretrained Llama-3-8B, our carefully selected student model. Results on three difficult AV datasets IMDb62, Blog-Auth, and Fanfiction show that CAVE generates high quality explanations (as measured by automatic and human evaluation) as well as competitive task accuracies.","url_abs":"https://arxiv.org/abs/2406.16672v2","url_pdf":"https://arxiv.org/pdf/2406.16672v2.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":"cave-controllable-authorship-verification","repo_url":"https://github.com/ink-usc/controllable-av-explanations","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"authorship-verification","task_name":"Authorship Verification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.16672","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}