{"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/socialiqa-commonsense-reasoning-about-social","title":"SocialIQA: Commonsense Reasoning about Social Interactions","arxiv_id":"1904.09728","date":"2019-04-22","proceeding":null,"authors":["Maarten Sap","Hannah Rashkin","Derek Chen","Ronan LeBras","Yejin Choi"],"abstract":"We introduce Social IQa, the first largescale benchmark for commonsense reasoning about social situations. Social IQa contains 38,000 multiple choice questions for probing emotional and social intelligence in a variety of everyday situations (e.g., Q: \"Jordan wanted to tell Tracy a secret, so Jordan leaned towards Tracy. Why did Jordan do this?\" A: \"Make sure no one else could hear\"). Through crowdsourcing, we collect commonsense questions along with correct and incorrect answers about social interactions, using a new framework that mitigates stylistic artifacts in incorrect answers by asking workers to provide the right answer to a different but related question. Empirical results show that our benchmark is challenging for existing question-answering models based on pretrained language models, compared to human performance (>20% gap). Notably, we further establish Social IQa as a resource for transfer learning of commonsense knowledge, achieving state-of-the-art performance on multiple commonsense reasoning tasks (Winograd Schemas, COPA).","url_abs":"https://arxiv.org/abs/1904.09728v3","url_pdf":"https://arxiv.org/pdf/1904.09728v3.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":"socialiqa-commonsense-reasoning-about-social","repo_url":"https://github.com/clear-nus/llm-human-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[{"slug":"social-iqa","name":"SIQA","full_name":"Social Interaction QA"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"BERT-SocialIQA 340M","rank_in_archive_order":31,"of":82,"metrics":{"Accuracy":"72.5"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"BERT-large 340M","rank_in_archive_order":39,"of":82,"metrics":{"Accuracy":"67"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"BERT-SocialIQA 340M","rank_in_archive_order":34,"of":60,"metrics":{"Accuracy":"83.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"BERT-large 340M","rank_in_archive_order":36,"of":60,"metrics":{"Accuracy":"80.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-social-iqa","task":"Question Answering","dataset":"SIQA","model":"BERT-large 340M (fine-tuned)","rank_in_archive_order":13,"of":24,"metrics":{"Accuracy":"64.5"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-social-iqa","task":"Question Answering","dataset":"SIQA","model":"BERT-base 110M (fine-tuned)","rank_in_archive_order":14,"of":24,"metrics":{"Accuracy":"63.1"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-social-iqa","task":"Question Answering","dataset":"SIQA","model":"GPT-1 117M (fine-tuned)","rank_in_archive_order":15,"of":24,"metrics":{"Accuracy":"63"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-social-iqa","task":"Question Answering","dataset":"SIQA","model":"Random chance baseline","rank_in_archive_order":24,"of":24,"metrics":{"Accuracy":"33.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.09728","atlas_url":"https://app.syntology.ai/?focus=1904.09728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09728"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/clear-nus/llm-human-model","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":5},"by_repo_kind":{"listed":{"samples":10,"ran":5,"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":"94d3875543a29881","entry":"generate_completion_t5","repo":"clear-nus/llm-human-model","repo_kind":"listed","path":"llm_utils.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/llm_utils.py","link_basis":"harvester_set","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":"94d3875543a29881"}},{"code_sha256_prefix":"f5e0055352d005b6","entry":"get_policy","repo":"clear-nus/llm-human-model","repo_kind":"listed","path":"table_clearing/table_clearing_trust_pomdp/evaluate/llm_policy.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/table_clearing/table_clearing_trust_pomdp/evaluate/llm_policy.py","link_basis":"harvester_set","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":"f5e0055352d005b6"}},{"code_sha256_prefix":"0e521abe5f775f14","entry":"llm_history_to_state","repo":"clear-nus/llm-human-model","repo_kind":"listed","path":"table_clearing/table_clearing_trust_pomdp/evaluate/llm_policy.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/table_clearing/table_clearing_trust_pomdp/evaluate/llm_policy.py","link_basis":"harvester_set","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":"0e521abe5f775f14"}},{"code_sha256_prefix":"af208036332d5f10","entry":"tokenize_answer_choices","repo":"clear-nus/llm-human-model","repo_kind":"listed","path":"llm_utils.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/llm_utils.py","link_basis":"harvester_set","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":"af208036332d5f10"}},{"code_sha256_prefix":"19ada76f6fdeda7b","entry":"translate_scenario_to_text","repo":"clear-nus/llm-human-model","repo_kind":"listed","path":"manners_db/manners_db_experiment_utils.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/manners_db/manners_db_experiment_utils.py","link_basis":"harvester_set","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":"19ada76f6fdeda7b"}},{"code_sha256_prefix":"d64904c8e899cc6f","entry":"create_prompt_davinci","repo":"clear-nus/llm-human-model","repo_kind":"listed","path":"manners_db/manners_db_experiment_utils.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/manners_db/manners_db_experiment_utils.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":"d64904c8e899cc6f"}},{"code_sha256_prefix":"3eae9cd2bc0dc803","entry":"create_prompt_t5","repo":"clear-nus/llm-human-model","repo_kind":"listed","path":"manners_db/manners_db_experiment_utils.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/manners_db/manners_db_experiment_utils.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":"3eae9cd2bc0dc803"}},{"code_sha256_prefix":"74e6e524d6f72496","entry":"get_plot_color","repo":"clear-nus/llm-human-model","repo_kind":"listed","path":"table_clearing/table_clearing_trust_pomdp/general-model/plots/colors.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/table_clearing/table_clearing_trust_pomdp/general-model/plots/colors.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":"74e6e524d6f72496"}},{"code_sha256_prefix":"34a3712826fa1956","entry":"get_probs_t5","repo":"clear-nus/llm-human-model","repo_kind":"listed","path":"llm_utils.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/llm_utils.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":"34a3712826fa1956"}},{"code_sha256_prefix":"d83e26bf6dda6392","entry":"get_shade_color","repo":"clear-nus/llm-human-model","repo_kind":"listed","path":"table_clearing/table_clearing_trust_pomdp/general-model/plots/colors.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/table_clearing/table_clearing_trust_pomdp/general-model/plots/colors.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":"d83e26bf6dda6392"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}