{"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/synthetic-knowledge-ingestion-towards","title":"Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models","arxiv_id":"2410.09629","date":"2024-10-12","proceeding":null,"authors":["Jiaxin Zhang","Wendi Cui","Yiran Huang","Kamalika Das","Sricharan Kumar"],"abstract":"Large language models (LLMs) are proficient in capturing factual knowledge across various domains. However, refining their capabilities on previously seen knowledge or integrating new knowledge from external sources remains a significant challenge. In this work, we propose a novel synthetic knowledge ingestion method called Ski, which leverages fine-grained synthesis, interleaved generation, and assemble augmentation strategies to construct high-quality data representations from raw knowledge sources. We then integrate Ski and its variations with three knowledge injection techniques: Retrieval Augmented Generation (RAG), Supervised Fine-tuning (SFT), and Continual Pre-training (CPT) to inject and refine knowledge in language models. Extensive empirical experiments are conducted on various question-answering tasks spanning finance, biomedicine, and open-generation domains to demonstrate that Ski significantly outperforms baseline methods by facilitating effective knowledge injection. We believe that our work is an important step towards enhancing the factual accuracy of LLM outputs by refining knowledge representation and injection capabilities.","url_abs":"https://arxiv.org/abs/2410.09629v1","url_pdf":"https://arxiv.org/pdf/2410.09629v1.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":"synthetic-knowledge-ingestion-towards","repo_url":"https://github.com/intuit-ai-research/knowledge-infused-ai/tree/main/synthetic-knowledge-ingestion","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.09629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09629"}},"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/intuit-ai-research/knowledge-infused-ai/tree/main/synthetic-knowledge-ingestion","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":1,"ran":3,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"9026d9da5d085bd4","entry":"compute_exact","repo":"intuit-ai-research/knowledge-infused-ai","repo_kind":"official","path":"synthetic-knowledge-ingestion/finetuning/ft_llama_factory.py","file_url":"https://github.com/intuit-ai-research/knowledge-infused-ai/blob/HEAD/synthetic-knowledge-ingestion/finetuning/ft_llama_factory.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"code_sha256_prefix":"d889e2a80bfef40d","entry":"data_split","repo":"intuit-ai-research/knowledge-infused-ai","repo_kind":"official","path":"synthetic-knowledge-ingestion/finetuning/data_preparation.py","file_url":"https://github.com/intuit-ai-research/knowledge-infused-ai/blob/HEAD/synthetic-knowledge-ingestion/finetuning/data_preparation.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":"d889e2a80bfef40d"}},{"code_sha256_prefix":"aa6bc32d9c17a2f1","entry":"get_tokens","repo":"intuit-ai-research/knowledge-infused-ai","repo_kind":"official","path":"synthetic-knowledge-ingestion/finetuning/ft_llama_factory.py","file_url":"https://github.com/intuit-ai-research/knowledge-infused-ai/blob/HEAD/synthetic-knowledge-ingestion/finetuning/ft_llama_factory.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa6bc32d9c17a2f1"}},{"code_sha256_prefix":"6a96435eba311b08","entry":"normalize_answer","repo":"intuit-ai-research/knowledge-infused-ai","repo_kind":"official","path":"synthetic-knowledge-ingestion/finetuning/ft_llama_factory.py","file_url":"https://github.com/intuit-ai-research/knowledge-infused-ai/blob/HEAD/synthetic-knowledge-ingestion/finetuning/ft_llama_factory.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a96435eba311b08"}},{"code_sha256_prefix":"800b0a442a1854a8","entry":"read_data","repo":"intuit-ai-research/knowledge-infused-ai","repo_kind":"official","path":"synthetic-knowledge-ingestion/finetuning/data_preparation.py","file_url":"https://github.com/intuit-ai-research/knowledge-infused-ai/blob/HEAD/synthetic-knowledge-ingestion/finetuning/data_preparation.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":"800b0a442a1854a8"}},{"code_sha256_prefix":"1b76e6eb9feedfc5","entry":"read_dataset","repo":"intuit-ai-research/knowledge-infused-ai","repo_kind":"official","path":"synthetic-knowledge-ingestion/finetuning/data_preparation.py","file_url":"https://github.com/intuit-ai-research/knowledge-infused-ai/blob/HEAD/synthetic-knowledge-ingestion/finetuning/data_preparation.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":"1b76e6eb9feedfc5"}},{"code_sha256_prefix":"17ab51ddeeed5908","entry":"get_ngram_sentences","repo":"intuit-ai-research/knowledge-infused-ai","repo_kind":"official","path":"synthetic-knowledge-ingestion/data_generation/utils.py","file_url":"https://github.com/intuit-ai-research/knowledge-infused-ai/blob/HEAD/synthetic-knowledge-ingestion/data_generation/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17ab51ddeeed5908"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}