{"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-generative-user-simulator-with-gpt-based","title":"A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems","arxiv_id":"2210.08692","date":"2022-10-17","proceeding":null,"authors":["Hong Liu","Yucheng Cai","Zhijian Ou","Yi Huang","Junlan Feng"],"abstract":"Building user simulators (USs) for reinforcement learning (RL) of task-oriented dialog systems (DSs) has gained more and more attention, which, however, still faces several fundamental challenges. First, it is unclear whether we can leverage pretrained language models to design, for example, GPT-2 based USs, to catch up and interact with the recently advanced GPT-2 based DSs. Second, an important ingredient in a US is that the user goal can be effectively incorporated and tracked; but how to flexibly integrate goal state tracking and develop an end-to-end trainable US for multi-domains has remained to be a challenge. In this work, we propose a generative user simulator (GUS) with GPT-2 based architecture and goal state tracking towards addressing the above two challenges. Extensive experiments are conducted on MultiWOZ2.1. Different DSs are trained via RL with GUS, the classic agenda-based user simulator (ABUS) and other ablation simulators respectively, and are compared for cross-model evaluation, corpus-based evaluation and human evaluation. The GUS achieves superior results in all three evaluation tasks.","url_abs":"https://arxiv.org/abs/2210.08692v2","url_pdf":"https://arxiv.org/pdf/2210.08692v2.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":"a-generative-user-simulator-with-gpt-based","repo_url":"https://github.com/thu-spmi/gus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.08692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08692"}},"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/thu-spmi/gus","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":"76660deb641b8569","entry":"Loss1","repo":"thu-spmi/gus","repo_kind":"official","path":"utils.py","file_url":"https://github.com/thu-spmi/gus/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"76660deb641b8569"}},{"code_sha256_prefix":"dde2e39bcafe4050","entry":"act_dict_to_aspn","repo":"thu-spmi/gus","repo_kind":"official","path":"prepare_data.py","file_url":"https://github.com/thu-spmi/gus/blob/HEAD/prepare_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dde2e39bcafe4050"}},{"code_sha256_prefix":"c20b24a9790d8f15","entry":"clean_text","repo":"thu-spmi/gus","repo_kind":"official","path":"clean_dataset.py","file_url":"https://github.com/thu-spmi/gus/blob/HEAD/clean_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c20b24a9790d8f15"}},{"code_sha256_prefix":"4c62f23ce8135bda","entry":"clean_time","repo":"thu-spmi/gus","repo_kind":"official","path":"clean_dataset.py","file_url":"https://github.com/thu-spmi/gus/blob/HEAD/clean_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c62f23ce8135bda"}},{"code_sha256_prefix":"e712e17d8551508b","entry":"goal_to_gpan","repo":"thu-spmi/gus","repo_kind":"official","path":"prepare_data.py","file_url":"https://github.com/thu-spmi/gus/blob/HEAD/prepare_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e712e17d8551508b"}},{"code_sha256_prefix":"ec89dac0427706f5","entry":"kl_loss","repo":"thu-spmi/gus","repo_kind":"official","path":"utils.py","file_url":"https://github.com/thu-spmi/gus/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec89dac0427706f5"}},{"code_sha256_prefix":"f971aae9c2c20b06","entry":"modified_encode","repo":"thu-spmi/gus","repo_kind":"official","path":"utils.py","file_url":"https://github.com/thu-spmi/gus/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f971aae9c2c20b06"}},{"code_sha256_prefix":"7f5a7dafc8e4429c","entry":"my_clean_text","repo":"thu-spmi/gus","repo_kind":"official","path":"clean_dataset.py","file_url":"https://github.com/thu-spmi/gus/blob/HEAD/clean_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7f5a7dafc8e4429c"}},{"code_sha256_prefix":"53bb02651160435f","entry":"test_collate_fn","repo":"thu-spmi/gus","repo_kind":"official","path":"reader.py","file_url":"https://github.com/thu-spmi/gus/blob/HEAD/reader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53bb02651160435f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}