{"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/legoeval-an-open-source-toolkit-for-dialogue","title":"LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing","arxiv_id":"2105.01992","date":"2021-05-05","proceeding":"ACL 2021 5","authors":["Yu Li","Josh Arnold","Feifan Yan","Weiyan Shi","Zhou Yu"],"abstract":"We present LEGOEval, an open-source toolkit that enables researchers to easily evaluate dialogue systems in a few lines of code using the online crowdsource platform, Amazon Mechanical Turk. Compared to existing toolkits, LEGOEval features a flexible task design by providing a Python API that maps to commonly used React.js interface components. Researchers can personalize their evaluation procedures easily with our built-in pages as if playing with LEGO blocks. Thus, LEGOEval provides a fast, consistent method for reproducing human evaluation results. Besides the flexible task design, LEGOEval also offers an easy API to review collected data.","url_abs":"https://arxiv.org/abs/2105.01992v1","url_pdf":"https://arxiv.org/pdf/2105.01992v1.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":"legoeval-an-open-source-toolkit-for-dialogue","repo_url":"https://github.com/yooli23/LEGOEval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.01992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01992"}},"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/yooli23/LEGOEval","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/Mephisto","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1},"found_in_text":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"dd4fc770109a751b","entry":"base_db_backed_call","repo":"facebookresearch/Mephisto","repo_kind":"found_in_text","path":"mephisto/data_model/_db_backed_meta.py","file_url":"https://github.com/facebookresearch/Mephisto/blob/HEAD/mephisto/data_model/_db_backed_meta.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"dd4fc770109a751b"}},{"code_sha256_prefix":"c478079d2e2e34f2","entry":"calculate_mturk_cost","repo":"yooli23/LEGOEval","repo_kind":"official","path":"app/mturk/mturk_utils.py","file_url":"https://github.com/yooli23/LEGOEval/blob/HEAD/app/mturk/mturk_utils.py","link_basis":"first_harvest_node","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":"c478079d2e2e34f2"}},{"code_sha256_prefix":"9da12bf2f3e069d7","entry":"check_mturk_balance","repo":"yooli23/LEGOEval","repo_kind":"official","path":"app/mturk/mturk_utils.py","file_url":"https://github.com/yooli23/LEGOEval/blob/HEAD/app/mturk/mturk_utils.py","link_basis":"first_harvest_node","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":"9da12bf2f3e069d7"}},{"code_sha256_prefix":"ddfb9ad6a1347789","entry":"convert_data","repo":"yooli23/LEGOEval","repo_kind":"official","path":"app/load_meena_blender_pairs.py","file_url":"https://github.com/yooli23/LEGOEval/blob/HEAD/app/load_meena_blender_pairs.py","link_basis":"first_harvest_node","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":"ddfb9ad6a1347789"}},{"code_sha256_prefix":"796dc260aec25b84","entry":"get_mturk_client","repo":"yooli23/LEGOEval","repo_kind":"official","path":"app/mturk/mturk_utils.py","file_url":"https://github.com/yooli23/LEGOEval/blob/HEAD/app/mturk/mturk_utils.py","link_basis":"first_harvest_node","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":"796dc260aec25b84"}},{"code_sha256_prefix":"bc212a39290078b7","entry":"load","repo":"yooli23/LEGOEval","repo_kind":"official","path":"app/load_meena_blender_pairs.py","file_url":"https://github.com/yooli23/LEGOEval/blob/HEAD/app/load_meena_blender_pairs.py","link_basis":"first_harvest_node","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":"bc212a39290078b7"}},{"code_sha256_prefix":"ac82dbca2ac74a9e","entry":"update","repo":"yooli23/LEGOEval","repo_kind":"official","path":"app/main_loop.py","file_url":"https://github.com/yooli23/LEGOEval/blob/HEAD/app/main_loop.py","link_basis":"first_harvest_node","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":"ac82dbca2ac74a9e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}