{"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/slang-new-concept-comprehension-of-large","title":"SLANG: New Concept Comprehension of Large Language Models","arxiv_id":"2401.12585","date":"2024-01-23","proceeding":null,"authors":["Lingrui Mei","Shenghua Liu","Yiwei Wang","Baolong Bi","Xueqi Cheng"],"abstract":"The dynamic nature of language, particularly evident in the realm of slang and memes on the Internet, poses serious challenges to the adaptability of large language models (LLMs). Traditionally anchored to static datasets, these models often struggle to keep up with the rapid linguistic evolution characteristic of online communities. This research aims to bridge this gap by enhancing LLMs' comprehension of the evolving new concepts on the Internet, without the high cost of continual retraining. In pursuit of this goal, we introduce $\\textbf{SLANG}$, a benchmark designed to autonomously integrate novel data and assess LLMs' ability to comprehend emerging concepts, alongside $\\textbf{FOCUS}$, an approach uses causal inference to enhance LLMs to understand new phrases and their colloquial context. Our benchmark and approach involves understanding real-world instances of linguistic shifts, serving as contextual beacons, to form more precise and contextually relevant connections between newly emerging expressions and their meanings. The empirical analysis shows that our causal inference-based approach outperforms the baseline methods in terms of precision and relevance in the comprehension of Internet slang and memes.","url_abs":"https://arxiv.org/abs/2401.12585v6","url_pdf":"https://arxiv.org/pdf/2401.12585v6.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":"slang-new-concept-comprehension-of-large","repo_url":"https://github.com/meirtz/focusonslang-toolbox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"causal-inference","task_name":"Causal Inference"}],"methods":[{"method_slug":"causal-inference","method_name":"Causal inference"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12585"}},"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/meirtz/focusonslang-toolbox","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":0,"samples":[{"code_sha256_prefix":"d9ab307b2ed5ee78","entry":"count_valid_words","repo":"meirtz/focusonslang-toolbox","repo_kind":"official","path":"clean_data.py","file_url":"https://github.com/meirtz/focusonslang-toolbox/blob/HEAD/clean_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9ab307b2ed5ee78"}},{"code_sha256_prefix":"978ce66ddf4e7b47","entry":"exact_match_score","repo":"meirtz/focusonslang-toolbox","repo_kind":"official","path":"eval_urban_f1.py","file_url":"https://github.com/meirtz/focusonslang-toolbox/blob/HEAD/eval_urban_f1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"978ce66ddf4e7b47"}},{"code_sha256_prefix":"e6e54258949655c8","entry":"f1_score","repo":"meirtz/focusonslang-toolbox","repo_kind":"official","path":"eval_urban_f1.py","file_url":"https://github.com/meirtz/focusonslang-toolbox/blob/HEAD/eval_urban_f1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e6e54258949655c8"}},{"code_sha256_prefix":"dae7ab386661a4f4","entry":"normalize_answer","repo":"meirtz/focusonslang-toolbox","repo_kind":"official","path":"eval_urban_f1.py","file_url":"https://github.com/meirtz/focusonslang-toolbox/blob/HEAD/eval_urban_f1.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dae7ab386661a4f4"}},{"code_sha256_prefix":"3a057603ec9a8fe6","entry":"parse_decision","repo":"meirtz/focusonslang-toolbox","repo_kind":"official","path":"clean_data.py","file_url":"https://github.com/meirtz/focusonslang-toolbox/blob/HEAD/clean_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a057603ec9a8fe6"}},{"code_sha256_prefix":"160deecc22d1848b","entry":"parse_knowledge_check_decision","repo":"meirtz/focusonslang-toolbox","repo_kind":"official","path":"clean_data.py","file_url":"https://github.com/meirtz/focusonslang-toolbox/blob/HEAD/clean_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160deecc22d1848b"}},{"code_sha256_prefix":"5790095a6bad01c3","entry":"replace_ignore_case","repo":"meirtz/focusonslang-toolbox","repo_kind":"official","path":"utils.py","file_url":"https://github.com/meirtz/focusonslang-toolbox/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5790095a6bad01c3"}},{"code_sha256_prefix":"42a531311fca2fed","entry":"sort_and_filter_data","repo":"meirtz/focusonslang-toolbox","repo_kind":"official","path":"utils.py","file_url":"https://github.com/meirtz/focusonslang-toolbox/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42a531311fca2fed"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}