{"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/augmenting-math-word-problems-via-iterative","title":"Augmenting Math Word Problems via Iterative Question Composing","arxiv_id":"2401.09003","date":"2024-01-17","proceeding":null,"authors":["Haoxiong Liu","Yifan Zhang","Yifan Luo","Andrew Chi-Chih Yao"],"abstract":"Despite the advancements in large language models (LLMs) for mathematical reasoning, solving competition-level math problems remains a significant challenge, especially for open-source LLMs without external tools. We introduce the MMIQC dataset, comprising a mixture of processed web data and synthetic question-response pairs, aimed at enhancing the mathematical reasoning capabilities of base language models. Models fine-tuned on MMIQC consistently surpass their counterparts in performance on the MATH benchmark across various model sizes. Notably, Qwen-72B-MMIQC achieves a 45.0% accuracy, exceeding the previous open-source state-of-the-art by 8.2% and outperforming the initial version GPT-4 released in 2023. Extensive evaluation results on Hungarian high school finals suggest that such improvement can generalize to unseen data. Our ablation study on MMIQC reveals that a large part of the improvement can be attributed to our novel augmentation method, Iterative Question Composing (IQC), which involves iteratively composing new questions from seed problems using an LLM and applying rejection sampling through another LLM.","url_abs":"https://arxiv.org/abs/2401.09003v5","url_pdf":"https://arxiv.org/pdf/2401.09003v5.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":"augmenting-math-word-problems-via-iterative","repo_url":"https://github.com/iiis-ai/iterativequestioncomposing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"math","task_name":"Math"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"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":"base","method_name":"BASE"},{"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":[{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"MMIQC-72B","rank_in_archive_order":66,"of":135,"metrics":{"Accuracy":"45.0","Parameters (Billions)":"72"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.09003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09003"}},"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/iiis-ai/iterativequestioncomposing","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"0393371470f8a3d7","entry":"detect_answer_in_box","repo":"iiis-ai/iterativequestioncomposing","repo_kind":"official","path":"utils/normalize_answer.py","file_url":"https://github.com/iiis-ai/iterativequestioncomposing/blob/HEAD/utils/normalize_answer.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":"0393371470f8a3d7"}},{"code_sha256_prefix":"6d7d0f055a8ddc0e","entry":"equals_with_timeout","repo":"iiis-ai/iterativequestioncomposing","repo_kind":"official","path":"utils/normalize_answer.py","file_url":"https://github.com/iiis-ai/iterativequestioncomposing/blob/HEAD/utils/normalize_answer.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":"6d7d0f055a8ddc0e"}},{"code_sha256_prefix":"e0e7e175a1f3e34c","entry":"extract_from_box","repo":"iiis-ai/iterativequestioncomposing","repo_kind":"official","path":"utils/normalize_answer.py","file_url":"https://github.com/iiis-ai/iterativequestioncomposing/blob/HEAD/utils/normalize_answer.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":"e0e7e175a1f3e34c"}},{"code_sha256_prefix":"6ad1dc04ebfc69b9","entry":"log_func_time","repo":"iiis-ai/iterativequestioncomposing","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/iiis-ai/iterativequestioncomposing/blob/HEAD/utils/misc.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":"6ad1dc04ebfc69b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}