{"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/the-semantic-hub-hypothesis-language-models","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","arxiv_id":"2411.04986","date":"2024-11-07","proceeding":null,"authors":["Zhaofeng Wu","Xinyan Velocity Yu","Dani Yogatama","Jiasen Lu","Yoon Kim"],"abstract":"Modern language models can process inputs across diverse languages and modalities. We hypothesize that models acquire this capability through learning a shared representation space across heterogeneous data types (e.g., different languages and modalities), which places semantically similar inputs near one another, even if they are from different modalities/languages. We term this the semantic hub hypothesis, following the hub-and-spoke model from neuroscience (Patterson et al., 2007) which posits that semantic knowledge in the human brain is organized through a transmodal semantic \"hub\" which integrates information from various modality-specific \"spokes\" regions. We first show that model representations for semantically equivalent inputs in different languages are similar in the intermediate layers, and that this space can be interpreted using the model's dominant pretraining language via the logit lens. This tendency extends to other data types, including arithmetic expressions, code, and visual/audio inputs. Interventions in the shared representation space in one data type also predictably affect model outputs in other data types, suggesting that this shared representations space is not simply a vestigial byproduct of large-scale training on broad data, but something that is actively utilized by the model during input processing.","url_abs":"https://arxiv.org/abs/2411.04986v2","url_pdf":"https://arxiv.org/pdf/2411.04986v2.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":"the-semantic-hub-hypothesis-language-models","repo_url":"https://github.com/ZhaofengWu/semantic-hub","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.04986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04986"}},"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/ZhaofengWu/semantic-hub","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"51ceab4ea3055e92","entry":"augment_data","repo":"ZhaofengWu/semantic-hub","repo_kind":"official","path":"multilingual/similarity.py","file_url":"https://github.com/ZhaofengWu/semantic-hub/blob/HEAD/multilingual/similarity.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"51ceab4ea3055e92"}},{"code_sha256_prefix":"6b6770605e6cb994","entry":"load_data","repo":"ZhaofengWu/semantic-hub","repo_kind":"official","path":"vision/similarity.py","file_url":"https://github.com/ZhaofengWu/semantic-hub/blob/HEAD/vision/similarity.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6b6770605e6cb994"}},{"code_sha256_prefix":"8eeaa325b202bdb8","entry":"read_gale_files","repo":"ZhaofengWu/semantic-hub","repo_kind":"official","path":"multilingual/similarity.py","file_url":"https://github.com/ZhaofengWu/semantic-hub/blob/HEAD/multilingual/similarity.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8eeaa325b202bdb8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}