{"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/symbol-llm-towards-foundational-symbol","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","arxiv_id":"2311.09278","date":"2023-11-15","proceeding":null,"authors":["Fangzhi Xu","Zhiyong Wu","Qiushi Sun","Siyu Ren","Fei Yuan","Shuai Yuan","Qika Lin","Yu Qiao","Jun Liu"],"abstract":"Although Large Language Models (LLMs) demonstrate remarkable ability in processing and generating human-like text, they do have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language(e.g., chemical molecular formula). Injecting a collection of symbolic data directly into the training of LLMs can be problematic, as it disregards the synergies among different symbolic families and overlooks the need for a balanced mixture of natural and symbolic data. In this work, we tackle these challenges from both a data and framework perspective and introduce Symbol-LLM series models. First, we curated a data collection consisting of 34 tasks and incorporating approximately 20 distinct symbolic families, intending to capture the interrelations and foster synergies between symbols. Then, a two-stage tuning framework succeeds in injecting symbolic knowledge without loss of the generality ability. Extensive experiments on both symbol- and NL-centric tasks demonstrate the balanced and superior performances of Symbol-LLM series models. The project page is https://xufangzhi.github.io/symbol-llm-page/.","url_abs":"https://arxiv.org/abs/2311.09278v2","url_pdf":"https://arxiv.org/pdf/2311.09278v2.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":"symbol-llm-towards-foundational-symbol","repo_url":"https://github.com/xufangzhi/envisions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"symbol-llm-towards-foundational-symbol","repo_url":"https://github.com/xufangzhi/genius","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"symbol-llm-towards-foundational-symbol","repo_url":"https://github.com/xufangzhi/phi-decoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.09278","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}