{"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/what-context-features-can-transformer","title":"What Context Features Can Transformer Language Models Use?","arxiv_id":"2106.08367","date":"2021-06-15","proceeding":"ACL 2021 5","authors":["Joe O'Connor","Jacob Andreas"],"abstract":"Transformer-based language models benefit from conditioning on contexts of hundreds to thousands of previous tokens. What aspects of these contexts contribute to accurate model prediction? We describe a series of experiments that measure usable information by selectively ablating lexical and structural information in transformer language models trained on English Wikipedia. In both mid- and long-range contexts, we find that several extremely destructive context manipulations -- including shuffling word order within sentences and deleting all words other than nouns -- remove less than 15% of the usable information. Our results suggest that long contexts, but not their detailed syntactic and propositional content, are important for the low perplexity of current transformer language models.","url_abs":"https://arxiv.org/abs/2106.08367v1","url_pdf":"https://arxiv.org/pdf/2106.08367v1.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":"what-context-features-can-transformer","repo_url":"https://github.com/lingo-mit/context-ablations","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.08367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08367"}},"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/lingo-mit/context-ablations","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"b14b50db4b6c6059","entry":"shuffle_first_half","repo":"lingo-mit/context-ablations","repo_kind":"official","path":"code/transformers/src/transformers/data/data_augmentation.py","file_url":"https://github.com/lingo-mit/context-ablations/blob/HEAD/code/transformers/src/transformers/data/data_augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b14b50db4b6c6059"}},{"code_sha256_prefix":"b8d233f0bceab517","entry":"shuffle_first_third","repo":"lingo-mit/context-ablations","repo_kind":"official","path":"code/transformers/src/transformers/data/data_augmentation.py","file_url":"https://github.com/lingo-mit/context-ablations/blob/HEAD/code/transformers/src/transformers/data/data_augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b8d233f0bceab517"}},{"code_sha256_prefix":"20176e8e8b8f42a7","entry":"shuffle_first_two_thirds","repo":"lingo-mit/context-ablations","repo_kind":"official","path":"code/transformers/src/transformers/data/data_augmentation.py","file_url":"https://github.com/lingo-mit/context-ablations/blob/HEAD/code/transformers/src/transformers/data/data_augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"20176e8e8b8f42a7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}