{"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/know-you-first-and-be-you-better-modeling","title":"Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles","arxiv_id":"2502.18968","date":"2025-02-26","proceeding":null,"authors":["Kuang Wang","Xianfei Li","Shenghao Yang","Li Zhou","Feng Jiang","Haizhou Li"],"abstract":"User simulators are crucial for replicating human interactions with dialogue systems, supporting both collaborative training and automatic evaluation, especially for large language models (LLMs). However, existing simulators often rely solely on text utterances, missing implicit user traits such as personality, speaking style, and goals. In contrast, persona-based methods lack generalizability, as they depend on predefined profiles of famous individuals or archetypes. To address these challenges, we propose User Simulator with implicit Profiles (USP), a framework that infers implicit user profiles from human-machine conversations and uses them to generate more personalized and realistic dialogues. We first develop an LLM-driven extractor with a comprehensive profile schema. Then, we refine the simulation through conditional supervised fine-tuning and reinforcement learning with cycle consistency, optimizing it at both the utterance and conversation levels. Finally, we adopt a diverse profile sampler to capture the distribution of real-world user profiles. Experimental results demonstrate that USP outperforms strong baselines in terms of authenticity and diversity while achieving comparable performance in consistency. Furthermore, dynamic multi-turn evaluations based on USP strongly align with mainstream benchmarks, demonstrating its effectiveness in real-world applications.","url_abs":"https://arxiv.org/abs/2502.18968v1","url_pdf":"https://arxiv.org/pdf/2502.18968v1.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":"know-you-first-and-be-you-better-modeling","repo_url":"https://github.com/wangkevin02/USP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"adopt","method_name":"ADOPT"},{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[{"slug":"lmsys-usp","name":"LMSYS-USP","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.18968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18968"}},"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":"deterministic:regex_extraction","url":"https://github.com/wangkevin02/USP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"54d306a042cb8dca","entry":"extract_profile_from_text","repo":"wangkevin02/USP","repo_kind":"official","path":"src/rlcc/OpenRLHF/remote_rm.py","file_url":"https://github.com/wangkevin02/USP/blob/HEAD/src/rlcc/OpenRLHF/remote_rm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54d306a042cb8dca"}},{"code_sha256_prefix":"1ec7b6e0fe041b67","entry":"extract_user_messages","repo":"wangkevin02/USP","repo_kind":"official","path":"src/auxiliary_models/profile_predictor/transfer_data_format.py","file_url":"https://github.com/wangkevin02/USP/blob/HEAD/src/auxiliary_models/profile_predictor/transfer_data_format.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ec7b6e0fe041b67"}},{"code_sha256_prefix":"4be9ec74064ab7dd","entry":"extract_user_messages","repo":"wangkevin02/USP","repo_kind":"official","path":"src/rlcc/OpenRLHF/remote_rm.py","file_url":"https://github.com/wangkevin02/USP/blob/HEAD/src/rlcc/OpenRLHF/remote_rm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4be9ec74064ab7dd"}},{"code_sha256_prefix":"fa2081602bac8f30","entry":"get_dataset_stats","repo":"wangkevin02/USP","repo_kind":"official","path":"src/auxiliary_models/ai_detect_model/my_dataset.py","file_url":"https://github.com/wangkevin02/USP/blob/HEAD/src/auxiliary_models/ai_detect_model/my_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa2081602bac8f30"}},{"code_sha256_prefix":"ca3514c46a1261d7","entry":"strip_sequence","repo":"wangkevin02/USP","repo_kind":"official","path":"src/rlcc/OpenRLHF/openrlhf/cli/serve_rm.py","file_url":"https://github.com/wangkevin02/USP/blob/HEAD/src/rlcc/OpenRLHF/openrlhf/cli/serve_rm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca3514c46a1261d7"}},{"code_sha256_prefix":"4081a5e23d9bc90f","entry":"strip_sequence","repo":"wangkevin02/USP","repo_kind":"official","path":"src/rlcc/OpenRLHF/remote_rm.py","file_url":"https://github.com/wangkevin02/USP/blob/HEAD/src/rlcc/OpenRLHF/remote_rm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4081a5e23d9bc90f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}