{"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/benchmarking-and-improving-compositional","title":"Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation","arxiv_id":"2404.04232","date":"2024-04-05","proceeding":null,"authors":["Tianqi Zhong","Zhaoyi Li","Quan Wang","Linqi Song","Ying WEI","Defu Lian","Zhendong Mao"],"abstract":"Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods. Nonetheless, a comprehensive compositional generalization evaluation benchmark of MCTG is still lacking. We propose CompMCTG, a benchmark encompassing diverse multi-aspect labeled datasets and a crafted three-dimensional evaluation protocol, to holistically evaluate the compositional generalization of MCTG approaches. We observe that existing MCTG works generally confront a noticeable performance drop in compositional testing. To mitigate this issue, we introduce Meta-MCTG, a training framework incorporating meta-learning, where we enable models to learn how to generalize by simulating compositional generalization scenarios in the training phase. We demonstrate the effectiveness of Meta-MCTG through achieving obvious improvement (by at most 3.64%) for compositional testing performance in 94.4% cases.","url_abs":"https://arxiv.org/abs/2404.04232v2","url_pdf":"https://arxiv.org/pdf/2404.04232v2.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":"benchmarking-and-improving-compositional","repo_url":"https://github.com/tqzhong/cg4mctg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.04232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04232"}},"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/tqzhong/cg4mctg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":"cc4e3483e9e21e24","entry":"check_train","repo":"tqzhong/cg4mctg","repo_kind":"official","path":"meta-mctg/load_dataset.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/load_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc4e3483e9e21e24"}},{"code_sha256_prefix":"2e66984a9ea41d4d","entry":"get_att_tokens_ids","repo":"tqzhong/cg4mctg","repo_kind":"official","path":"meta-mctg/dcg_meta.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/dcg_meta.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e66984a9ea41d4d"}},{"code_sha256_prefix":"27e90bbc00602ee5","entry":"get_support_combs","repo":"tqzhong/cg4mctg","repo_kind":"official","path":"meta-mctg/contrastive_prefix_meta.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/contrastive_prefix_meta.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27e90bbc00602ee5"}},{"code_sha256_prefix":"bb747457b90d9661","entry":"padding_fuse_fn","repo":"tqzhong/cg4mctg","repo_kind":"official","path":"meta-mctg/contrastive_prefix_meta.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/contrastive_prefix_meta.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb747457b90d9661"}},{"code_sha256_prefix":"a7934fa0e86ec35f","entry":"padding_fuse_fn","repo":"tqzhong/cg4mctg","repo_kind":"official","path":"meta-mctg/dcg_meta.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/dcg_meta.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7934fa0e86ec35f"}},{"code_sha256_prefix":"9dbd25c2cddac479","entry":"tokenize","repo":"tqzhong/cg4mctg","repo_kind":"official","path":"meta-mctg/contrastive_prefix_meta.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/contrastive_prefix_meta.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9dbd25c2cddac479"}},{"code_sha256_prefix":"59ac6441acc40e2e","entry":"tokenize","repo":"tqzhong/cg4mctg","repo_kind":"official","path":"meta-mctg/ctrl_meta.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/ctrl_meta.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59ac6441acc40e2e"}},{"code_sha256_prefix":"6c3ca0db0954ed64","entry":"tokenize","repo":"tqzhong/cg4mctg","repo_kind":"official","path":"meta-mctg/dcg_meta.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/dcg_meta.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c3ca0db0954ed64"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}