{"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/emergent-communication-of-generalizations","title":"Emergent Communication of Generalizations","arxiv_id":"2106.02668","date":"2021-06-04","proceeding":"NeurIPS 2021 12","authors":["Jesse Mu","Noah Goodman"],"abstract":"To build agents that can collaborate effectively with others, recent research has trained artificial agents to communicate with each other in Lewis-style referential games. However, this often leads to successful but uninterpretable communication. We argue that this is due to the game objective: communicating about a single object in a shared visual context is prone to overfitting and does not encourage language useful beyond concrete reference. In contrast, human language conveys a rich variety of abstract ideas. To promote such skills, we propose games that require communicating generalizations over sets of objects representing abstract visual concepts, optionally with separate contexts for each agent. We find that these games greatly improve systematicity and interpretability of the learned languages, according to several metrics in the literature. Finally, we propose a method for identifying logical operations embedded in the emergent languages by learning an approximate compositional reconstruction of the language.","url_abs":"https://arxiv.org/abs/2106.02668v2","url_pdf":"https://arxiv.org/pdf/2106.02668v2.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":"emergent-communication-of-generalizations","repo_url":"https://github.com/jayelm/emergent-generalization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.02668","atlas_url":"https://app.syntology.ai/?focus=2106.02668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02668"}},"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/jayelm/emergent-generalization","reach":null}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1},"community":{"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":4,"samples":[{"code_sha256_prefix":"2a69c9dcc7c7adf8","entry":"get_mask_from_length","repo":"jayelm/emergent-generalization","repo_kind":"official","path":"code/acre.py","file_url":"https://github.com/jayelm/emergent-generalization/blob/HEAD/code/acre.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2a69c9dcc7c7adf8"}},{"code_sha256_prefix":"f174bf022715ec11","entry":"OpT","repo":"jayelm/emergent-generalization","repo_kind":"official","path":"code/acre.py","file_url":"https://github.com/jayelm/emergent-generalization/blob/HEAD/code/acre.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f174bf022715ec11"}},{"code_sha256_prefix":"f6dfb9c04a38264a","entry":"get_length_from_output","repo":"jayelm/emergent-generalization","repo_kind":"official","path":"code/acre.py","file_url":"https://github.com/jayelm/emergent-generalization/blob/HEAD/code/acre.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f6dfb9c04a38264a"}},{"code_sha256_prefix":"16fca11fc3f662f3","entry":"get_transformer_encoder_decoder","repo":"jayelm/emergent-generalization","repo_kind":"official","path":"code/acre.py","file_url":"https://github.com/jayelm/emergent-generalization/blob/HEAD/code/acre.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"16fca11fc3f662f3"}},{"code_sha256_prefix":"206645d1cc5664cb","entry":"preprocess_hints","repo":"jayelm/minishapeworld","repo_kind":"community","path":"scripts/convert_l3.py","file_url":"https://github.com/jayelm/minishapeworld/blob/HEAD/scripts/convert_l3.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"206645d1cc5664cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}