{"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/phased-instruction-fine-tuning-for-large","title":"Phased Instruction Fine-Tuning for Large Language Models","arxiv_id":"2406.04371","date":"2024-06-01","proceeding":null,"authors":["Wei Pang","Chuan Zhou","Xiao-Hua Zhou","Xiaojie Wang"],"abstract":"Instruction Fine-Tuning enhances pre-trained language models from basic next-word prediction to complex instruction-following. However, existing One-off Instruction Fine-Tuning (One-off IFT) method, applied on a diverse instruction, may not effectively boost models' adherence to instructions due to the simultaneous handling of varying instruction complexities. To improve this, Phased Instruction Fine-Tuning (Phased IFT) is proposed, based on the idea that learning to follow instructions is a gradual process. It assesses instruction difficulty using GPT-4, divides the instruction data into subsets of increasing difficulty, and uptrains the model sequentially on these subsets. Experiments with Llama-2 7B/13B/70B, Llama3 8/70B and Mistral-7B models using Alpaca data show that Phased IFT significantly outperforms One-off IFT, supporting the progressive alignment hypothesis and providing a simple and efficient way to enhance large language models. Codes and datasets from our experiments are freely available at https://github.com/xubuvd/PhasedSFT.","url_abs":"https://arxiv.org/abs/2406.04371v2","url_pdf":"https://arxiv.org/pdf/2406.04371v2.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":"phased-instruction-fine-tuning-for-large","repo_url":"https://github.com/xubuvd/phasedsft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.04371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04371"}},"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/xubuvd/phasedsft","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":"3afb17c8a1be8359","entry":"check_alternate_human_gpt","repo":"xubuvd/phasedsft","repo_kind":"official","path":"xllm/xllm_dataset.py","file_url":"https://github.com/xubuvd/phasedsft/blob/HEAD/xllm/xllm_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3afb17c8a1be8359"}},{"code_sha256_prefix":"01edd35282158f9c","entry":"code","repo":"xubuvd/phasedsft","repo_kind":"official","path":"xllm/packed_dataset.py","file_url":"https://github.com/xubuvd/phasedsft/blob/HEAD/xllm/packed_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01edd35282158f9c"}},{"code_sha256_prefix":"5d17b604c968b41d","entry":"get_json_list","repo":"xubuvd/phasedsft","repo_kind":"official","path":"evaluation/win_tie_loss_stat.py","file_url":"https://github.com/xubuvd/phasedsft/blob/HEAD/evaluation/win_tie_loss_stat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d17b604c968b41d"}},{"code_sha256_prefix":"e56e56ce6b668fc7","entry":"load_raw_data","repo":"xubuvd/phasedsft","repo_kind":"official","path":"xllm/xllm_dataset.py","file_url":"https://github.com/xubuvd/phasedsft/blob/HEAD/xllm/xllm_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e56e56ce6b668fc7"}},{"code_sha256_prefix":"d31a77986dbba07f","entry":"load_single_file","repo":"xubuvd/phasedsft","repo_kind":"official","path":"xllm/xllm_dataset.py","file_url":"https://github.com/xubuvd/phasedsft/blob/HEAD/xllm/xllm_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d31a77986dbba07f"}},{"code_sha256_prefix":"b82ea85435a2d02e","entry":"nvtx_range","repo":"xubuvd/phasedsft","repo_kind":"official","path":"xllm/utils/profile.py","file_url":"https://github.com/xubuvd/phasedsft/blob/HEAD/xllm/utils/profile.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b82ea85435a2d02e"}},{"code_sha256_prefix":"d9b9b1f09f63f865","entry":"parse_score","repo":"xubuvd/phasedsft","repo_kind":"official","path":"evaluation/win_tie_loss_stat.py","file_url":"https://github.com/xubuvd/phasedsft/blob/HEAD/evaluation/win_tie_loss_stat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9b9b1f09f63f865"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}