{"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/i-learn-better-if-you-speak-my-language","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","arxiv_id":"2402.11192","date":"2024-02-17","proceeding":null,"authors":["Xuan Ren","Biao Wu","Lingqiao Liu"],"abstract":"This paper explores an intriguing observation: fine-tuning a large language model (LLM) with responses generated by a LLM often yields better results than using responses generated by humans, particularly in reasoning tasks. We conduct an in-depth investigation to understand why this occurs. Contrary to the common belief that these instances is due to the more detailed nature of LLM-generated content, our study identifies another contributing factor: an LLM is inherently more \"familiar\" with LLM generated responses. This familiarity is evidenced by lower perplexity before fine-tuning. We design a series of experiments to understand the impact of the \"familiarity\" and our conclusion reveals that this \"familiarity\" significantly impacts learning performance. Training with LLM-generated responses not only enhances performance but also helps maintain the model's capabilities in other reasoning tasks after fine-tuning on a specific task.","url_abs":"https://arxiv.org/abs/2402.11192v4","url_pdf":"https://arxiv.org/pdf/2402.11192v4.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":"i-learn-better-if-you-speak-my-language","repo_url":"https://github.com/xuanren4470/i-learn-better-if-you-speak-my-language","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"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.11192","atlas_url":"https://app.syntology.ai/?focus=2402.11192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11192"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/XuanRen4470/I-Learn-Better-If-You-Speak-My-Language","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":4},"by_repo_kind":{"official":{"samples":9,"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":9,"samples":[{"code_sha256_prefix":"2d522f3ca6d07d59","entry":"check_intermediate_file_available","repo":"XuanRen4470/I-Learn-Better-If-You-Speak-My-Language","repo_kind":"official","path":"utils/llama_factory_data_file_processor.py","file_url":"https://github.com/XuanRen4470/I-Learn-Better-If-You-Speak-My-Language/blob/HEAD/utils/llama_factory_data_file_processor.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":"2d522f3ca6d07d59"}},{"code_sha256_prefix":"98c5710084f41409","entry":"find_last_boxed_number_with_simple_format","repo":"XuanRen4470/I-Learn-Better-If-You-Speak-My-Language","repo_kind":"official","path":"utils/data_loader_backup_apr_13.py","file_url":"https://github.com/XuanRen4470/I-Learn-Better-If-You-Speak-My-Language/blob/HEAD/utils/data_loader_backup_apr_13.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":"98c5710084f41409"}},{"code_sha256_prefix":"9973e42e6f16dd4c","entry":"in_context_learning_examples","repo":"XuanRen4470/I-Learn-Better-If-You-Speak-My-Language","repo_kind":"official","path":"utils/data_loader_in_context.py","file_url":"https://github.com/XuanRen4470/I-Learn-Better-If-You-Speak-My-Language/blob/HEAD/utils/data_loader_in_context.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":"9973e42e6f16dd4c"}},{"code_sha256_prefix":"6fc3fba01949fae2","entry":"llemma_7b_muinstruct_camelmath_complete_instruction","repo":"XuanRen4470/I-Learn-Better-If-You-Speak-My-Language","repo_kind":"official","path":"utils/data_loader.py","file_url":"https://github.com/XuanRen4470/I-Learn-Better-If-You-Speak-My-Language/blob/HEAD/utils/data_loader.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":"6fc3fba01949fae2"}},{"code_sha256_prefix":"a277781067f69a3b","entry":"meta_math_complete_instruction","repo":"XuanRen4470/I-Learn-Better-If-You-Speak-My-Language","repo_kind":"official","path":"utils/data_loader.py","file_url":"https://github.com/XuanRen4470/I-Learn-Better-If-You-Speak-My-Language/blob/HEAD/utils/data_loader.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":"a277781067f69a3b"}},{"code_sha256_prefix":"b1792e134b9bbe38","entry":"ZERO_SHOT_EVALUATION","repo":"XuanRen4470/I-Learn-Better-If-You-Speak-My-Language","repo_kind":"official","path":"utils/perform_task.py","file_url":"https://github.com/XuanRen4470/I-Learn-Better-If-You-Speak-My-Language/blob/HEAD/utils/perform_task.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":"b1792e134b9bbe38"}},{"code_sha256_prefix":"e71103749e6653b8","entry":"compute_similarity_scores","repo":"XuanRen4470/I-Learn-Better-If-You-Speak-My-Language","repo_kind":"official","path":"utils/in_context_perplexity_measurement_function.py","file_url":"https://github.com/XuanRen4470/I-Learn-Better-If-You-Speak-My-Language/blob/HEAD/utils/in_context_perplexity_measurement_function.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":"e71103749e6653b8"}},{"code_sha256_prefix":"020b587445b0a505","entry":"compute_similarity_scores_using_probabilities","repo":"XuanRen4470/I-Learn-Better-If-You-Speak-My-Language","repo_kind":"official","path":"utils/in_context_perplexity_measurement_function.py","file_url":"https://github.com/XuanRen4470/I-Learn-Better-If-You-Speak-My-Language/blob/HEAD/utils/in_context_perplexity_measurement_function.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":"020b587445b0a505"}},{"code_sha256_prefix":"89e1d1b2368bed77","entry":"get_mean_embedding_without_stopwords","repo":"XuanRen4470/I-Learn-Better-If-You-Speak-My-Language","repo_kind":"official","path":"utils/in_context_perplexity_measurement_function.py","file_url":"https://github.com/XuanRen4470/I-Learn-Better-If-You-Speak-My-Language/blob/HEAD/utils/in_context_perplexity_measurement_function.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":"89e1d1b2368bed77"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}