{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/human-parity-on-commonsenseqa-augmenting-self","title":"Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention","arxiv_id":"2112.03254","date":"2021-12-06","proceeding":null,"authors":["Yichong Xu","Chenguang Zhu","Shuohang Wang","Siqi Sun","Hao Cheng","Xiaodong Liu","Jianfeng Gao","Pengcheng He","Michael Zeng","Xuedong Huang"],"abstract":"Most of today's AI systems focus on using self-attention mechanisms and transformer architectures on large amounts of diverse data to achieve impressive performance gains. In this paper, we propose to augment the transformer architecture with an external attention mechanism to bring external knowledge and context to bear. By integrating external information into the prediction process, we hope to reduce the need for ever-larger models and increase the democratization of AI systems. We find that the proposed external attention mechanism can significantly improve the performance of existing AI systems, allowing practitioners to easily customize foundation AI models to many diverse downstream applications. In particular, we focus on the task of Commonsense Reasoning, demonstrating that the proposed external attention mechanism can augment existing transformer models and significantly improve the model's reasoning capabilities. The proposed system, Knowledgeable External Attention for commonsense Reasoning (KEAR), reaches human parity on the open CommonsenseQA research benchmark with an accuracy of 89.4\\% in comparison to the human accuracy of 88.9\\%.","url_abs":"https://arxiv.org/abs/2112.03254v3","url_pdf":"https://arxiv.org/pdf/2112.03254v3.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":"human-parity-on-commonsenseqa-augmenting-self","repo_url":"https://github.com/microsoft/kear","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"human-parity-on-commonsenseqa-augmenting-self","repo_url":"https://github.com/microsoft/DEKCOR-CommonsenseQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/common-sense-reasoning-on-commonsenseqa","task":"Common Sense Reasoning","dataset":"CommonsenseQA","model":"DeBERTaV3-large+KEAR","rank_in_archive_order":2,"of":38,"metrics":{"Accuracy":"91.2"},"uses_additional_data":true},{"leaderboard":"/sota/common-sense-reasoning-on-commonsenseqa","task":"Common Sense Reasoning","dataset":"CommonsenseQA","model":"KEAR","rank_in_archive_order":4,"of":38,"metrics":{"Accuracy":"89.4"},"uses_additional_data":true},{"leaderboard":"/sota/common-sense-reasoning-on-commonsenseqa","task":"Common Sense Reasoning","dataset":"CommonsenseQA","model":"GPT-3 Direct Finetuned","rank_in_archive_order":17,"of":38,"metrics":{"Accuracy":"73.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.03254","atlas_url":"https://app.syntology.ai/?focus=2112.03254","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2112.03254"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2112.03254\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2112.03254"},"call":"get_concepts_for_paper(arxiv_id=\"2112.03254\")"}],"by_repo":[{"repo":"microsoft/kear","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"microsoft/DEKCOR-CommonsenseQA","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1e99b25f8a77edb6259ccf1dd019fc289269ff516f23cf0fc9989df0801b5322","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}