{"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/babysit-a-language-model-from-scratch","title":"Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations","arxiv_id":"2405.13828","date":"2024-05-22","proceeding":null,"authors":["Ziqiao Ma","Zekun Wang","Joyce Chai"],"abstract":"Humans are efficient language learners and inherently social creatures. Our language development is largely shaped by our social interactions, for example, the demonstration and feedback from caregivers. Contrary to human language learning, recent advancements in large language models have primarily adopted a non-interactive training paradigm, and refined pre-trained models through feedback afterward. In this work, we explore how corrective feedback from interactions influences neural language acquisition from scratch through systematically controlled experiments, assessing whether it contributes to word learning efficiency in language models. We introduce a trial-and-demonstration (TnD) learning framework that incorporates three distinct components: student trials, teacher demonstrations, and a reward conditioned on language competence at various developmental stages. Our experiments reveal that the TnD approach accelerates word acquisition for student models of equal and smaller numbers of parameters, and we highlight the significance of both trials and demonstrations. We further show that the teacher's choices of words influence students' word-specific learning efficiency, and a practice-makes-perfect effect is evident by a strong correlation between the frequency of words in trials and their respective learning curves. Our findings suggest that interactive language learning, with teacher demonstrations and active trials, can facilitate efficient word learning in language models.","url_abs":"https://arxiv.org/abs/2405.13828v2","url_pdf":"https://arxiv.org/pdf/2405.13828v2.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":"babysit-a-language-model-from-scratch","repo_url":"https://github.com/sled-group/TnD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-acquisition","task_name":"Language Acquisition"},{"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=2405.13828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13828"}},"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/sled-group/TnD","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_violates":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":5,"samples":[{"code_sha256_prefix":"6e1646c98c4b9485","entry":"has_accumulated_gradients","repo":"sled-group/TnD","repo_kind":"official","path":"TnD/EPPOTrainer.py","file_url":"https://github.com/sled-group/TnD/blob/HEAD/TnD/EPPOTrainer.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":"6e1646c98c4b9485"}},{"code_sha256_prefix":"2e6d1b6660ada150","entry":"parse_generated_text","repo":"sled-group/tnd","repo_kind":"official","path":"reward_model/train_reward.py","file_url":"https://github.com/sled-group/tnd/blob/HEAD/reward_model/train_reward.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e6d1b6660ada150"}},{"code_sha256_prefix":"992cd8629a854c72","entry":"save_condition","repo":"sled-group/tnd","repo_kind":"official","path":"reward_model/train_reward.py","file_url":"https://github.com/sled-group/tnd/blob/HEAD/reward_model/train_reward.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"992cd8629a854c72"}},{"code_sha256_prefix":"9122b52becc847d5","entry":"train_model","repo":"sled-group/TnD","repo_kind":"official","path":"TnD/trainer_util.py","file_url":"https://github.com/sled-group/TnD/blob/HEAD/TnD/trainer_util.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":"9122b52becc847d5"}},{"code_sha256_prefix":"232342427f89b8b9","entry":"update_scheduler","repo":"sled-group/TnD","repo_kind":"official","path":"TnD/trainer_util.py","file_url":"https://github.com/sled-group/TnD/blob/HEAD/TnD/trainer_util.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":"232342427f89b8b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}