{"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/bridging-information-theoretic-and-geometric","title":"Bridging Information-Theoretic and Geometric Compression in Language Models","arxiv_id":"2310.13620","date":"2023-10-20","proceeding":null,"authors":["Emily Cheng","Corentin Kervadec","Marco Baroni"],"abstract":"For a language model (LM) to faithfully model human language, it must compress vast, potentially infinite information into relatively few dimensions. We propose analyzing compression in (pre-trained) LMs from two points of view: geometric and information-theoretic. We demonstrate that the two views are highly correlated, such that the intrinsic geometric dimension of linguistic data predicts their coding length under the LM. We then show that, in turn, high compression of a linguistic dataset predicts rapid adaptation to that dataset, confirming that being able to compress linguistic information is an important part of successful LM performance. As a practical byproduct of our analysis, we evaluate a battery of intrinsic dimension estimators for the first time on linguistic data, showing that only some encapsulate the relationship between information-theoretic compression, geometric compression, and ease-of-adaptation.","url_abs":"https://arxiv.org/abs/2310.13620v2","url_pdf":"https://arxiv.org/pdf/2310.13620v2.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":"bridging-information-theoretic-and-geometric","repo_url":"https://github.com/chengemily1/id_bridging","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.13620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13620"}},"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/chengemily1/id_bridging","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"1c268aca91d19bfb","entry":"generate_tokens","repo":"chengemily1/id_bridging","repo_kind":"official","path":"lm-corpus.py","file_url":"https://github.com/chengemily1/id_bridging/blob/HEAD/lm-corpus.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c268aca91d19bfb"}},{"code_sha256_prefix":"e2f45ffc4ea6a166","entry":"last_token_rep","repo":"chengemily1/id_bridging","repo_kind":"official","path":"id_bootstrap.py","file_url":"https://github.com/chengemily1/id_bridging/blob/HEAD/id_bootstrap.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e2f45ffc4ea6a166"}},{"code_sha256_prefix":"1139c7a3c2d72424","entry":"last_token_rep","repo":"chengemily1/id_bridging","repo_kind":"official","path":"intrinsic_dimension.py","file_url":"https://github.com/chengemily1/id_bridging/blob/HEAD/intrinsic_dimension.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1139c7a3c2d72424"}},{"code_sha256_prefix":"48362eb1ec3147dc","entry":"pool_tensor","repo":"chengemily1/id_bridging","repo_kind":"official","path":"id_bootstrap.py","file_url":"https://github.com/chengemily1/id_bridging/blob/HEAD/id_bootstrap.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48362eb1ec3147dc"}},{"code_sha256_prefix":"84321ea24976aa4e","entry":"resize_tensor","repo":"chengemily1/id_bridging","repo_kind":"official","path":"id_bootstrap.py","file_url":"https://github.com/chengemily1/id_bridging/blob/HEAD/id_bootstrap.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"84321ea24976aa4e"}},{"code_sha256_prefix":"0c6d4c00ac20cd62","entry":"init_model","repo":"chengemily1/id_bridging","repo_kind":"official","path":"lm-corpus.py","file_url":"https://github.com/chengemily1/id_bridging/blob/HEAD/lm-corpus.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":"0c6d4c00ac20cd62"}},{"code_sha256_prefix":"783fad2cce6ae106","entry":"pick_batch_and_generate","repo":"chengemily1/id_bridging","repo_kind":"official","path":"lm-corpus.py","file_url":"https://github.com/chengemily1/id_bridging/blob/HEAD/lm-corpus.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":"783fad2cce6ae106"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}