{"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/lift-language-interfaced-fine-tuning-for-non","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","arxiv_id":"2206.06565","date":"2022-06-14","proceeding":null,"authors":["Tuan Dinh","Yuchen Zeng","Ruisu Zhang","Ziqian Lin","Michael Gira","Shashank Rajput","Jy-yong Sohn","Dimitris Papailiopoulos","Kangwook Lee"],"abstract":"Fine-tuning pretrained language models (LMs) without making any architectural changes has become a norm for learning various language downstream tasks. However, for non-language downstream tasks, a common practice is to employ task-specific designs for input, output layers, and loss functions. For instance, it is possible to fine-tune an LM into an MNIST classifier by replacing the word embedding layer with an image patch embedding layer, the word token output layer with a 10-way output layer, and the word prediction loss with a 10-way classification loss, respectively. A natural question arises: Can LM fine-tuning solve non-language downstream tasks without changing the model architecture or loss function? To answer this, we propose Language-Interfaced Fine-Tuning (LIFT) and study its efficacy and limitations by conducting an extensive empirical study on a suite of non-language classification and regression tasks. LIFT does not make any changes to the model architecture or loss function, and it solely relies on the natural language interface, enabling \"no-code machine learning with LMs.\" We find that LIFT performs comparably well across a wide range of low-dimensional classification and regression tasks, matching the performances of the best baselines in many cases, especially for the classification tasks. We also report experimental results on the fundamental properties of LIFT, including inductive bias, robustness, and sample complexity. We also analyze the effect of pretraining on LIFT and a few properties/techniques specific to LIFT, e.g., context-aware learning via appropriate prompting, calibrated predictions, data generation, and two-stage fine-tuning. Our code is available at https://github.com/UW-Madison-Lee-Lab/LanguageInterfacedFineTuning.","url_abs":"https://arxiv.org/abs/2206.06565v4","url_pdf":"https://arxiv.org/pdf/2206.06565v4.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":"lift-language-interfaced-fine-tuning-for-non","repo_url":"https://github.com/uw-madison-lee-lab/languageinterfacedfinetuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2206.06565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06565"}},"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/uw-madison-lee-lab/languageinterfacedfinetuning","reach":null}],"summary":{"ran_violates":2,"ran_draft_wrong":1,"ran_honours":2},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"4c9db8e7368f3b29","entry":"RMSE","repo":"uw-madison-lee-lab/languageinterfacedfinetuning","repo_kind":"official","path":"regression/utils/GPTJFineTuner.py","file_url":"https://github.com/uw-madison-lee-lab/languageinterfacedfinetuning/blob/HEAD/regression/utils/GPTJFineTuner.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c9db8e7368f3b29"}},{"code_sha256_prefix":"9ecaea61d46c1d10","entry":"extract_completion","repo":"uw-madison-lee-lab/languageinterfacedfinetuning","repo_kind":"official","path":"classification/run_exps/run_gpt3_mnist.py","file_url":"https://github.com/uw-madison-lee-lab/languageinterfacedfinetuning/blob/HEAD/classification/run_exps/run_gpt3_mnist.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ecaea61d46c1d10"}},{"code_sha256_prefix":"a57290aeaf839125","entry":"L2error","repo":"uw-madison-lee-lab/languageinterfacedfinetuning","repo_kind":"official","path":"regression/utils/GPTJFineTuner.py","file_url":"https://github.com/uw-madison-lee-lab/languageinterfacedfinetuning/blob/HEAD/regression/utils/GPTJFineTuner.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a57290aeaf839125"}},{"code_sha256_prefix":"43db224359a04025","entry":"RMSE_woo","repo":"uw-madison-lee-lab/languageinterfacedfinetuning","repo_kind":"official","path":"regression/utils/GPTJFineTuner.py","file_url":"https://github.com/uw-madison-lee-lab/languageinterfacedfinetuning/blob/HEAD/regression/utils/GPTJFineTuner.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43db224359a04025"}},{"code_sha256_prefix":"10f914d510584661","entry":"prompt2value","repo":"uw-madison-lee-lab/languageinterfacedfinetuning","repo_kind":"official","path":"classification/run_exps/run_gpt3_mnist.py","file_url":"https://github.com/uw-madison-lee-lab/languageinterfacedfinetuning/blob/HEAD/classification/run_exps/run_gpt3_mnist.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10f914d510584661"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}