{"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/overcoming-barriers-to-skill-injection-in","title":"Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic","arxiv_id":"2211.02098","date":"2022-11-03","proceeding":null,"authors":["Mandar Sharma","Nikhil Muralidhar","Naren Ramakrishnan"],"abstract":"Through their transfer learning abilities, highly-parameterized large pre-trained language models have dominated the NLP landscape for a multitude of downstream language tasks. Though linguistically proficient, the inability of these models to incorporate the learning of non-linguistic entities (numerals and arithmetic reasoning) limits their usage for tasks that require numeric comprehension or strict mathematical reasoning. However, as we illustrate in this paper, building a general purpose language model that also happens to be proficient in mathematical reasoning is not as straight-forward as training it on a numeric dataset. In this work, we develop a novel framework that enables language models to be mathematically proficient while retaining their linguistic prowess. Specifically, we offer information-theoretic interventions to overcome the catastrophic forgetting of linguistic skills that occurs while injecting non-linguistic skills into language models.","url_abs":"https://arxiv.org/abs/2211.02098v1","url_pdf":"https://arxiv.org/pdf/2211.02098v1.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":"overcoming-barriers-to-skill-injection-in","repo_url":"https://github.com/mandar-sharma/overcomingbarriers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.02098","atlas_url":"https://app.syntology.ai/?focus=2211.02098","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}