{"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/sciriff-a-resource-to-enhance-language-model","title":"SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature","arxiv_id":"2406.07835","date":"2024-06-10","proceeding":null,"authors":["David Wadden","Kejian Shi","Jacob Morrison","Aakanksha Naik","Shruti Singh","Nitzan Barzilay","Kyle Lo","Tom Hope","Luca Soldaini","Shannon Zejiang Shen","Doug Downey","Hannaneh Hajishirzi","Arman Cohan"],"abstract":"We present SciRIFF (Scientific Resource for Instruction-Following and Finetuning), a dataset of 137K instruction-following demonstrations for 54 tasks covering five essential scientific literature understanding capabilities: information extraction, summarization, question answering, claim verification, and classification. SciRIFF demonstrations are notable for their long input contexts, detailed task specifications, and complex structured outputs. While instruction-following resources are available in specific domains such as clinical medicine and chemistry, SciRIFF is the first dataset focused on extracting and synthesizing information from research literature across a wide range of scientific fields. To demonstrate the utility of SciRIFF, we develop a sample-efficient strategy to adapt a general instruction-following model for science by performing additional finetuning on a mix of general-domain and SciRIFF demonstrations. In evaluations on nine held-out scientific tasks, our model -- called SciTulu -- improves over a strong LLM baseline by 28.1% and 6.5% at the 7B and 70B scales respectively, while maintaining general instruction-following performance within 2% of the baseline. We are optimistic that SciRIFF will facilitate the development and evaluation of LLMs to help researchers navigate the ever-growing body of scientific literature. We release our dataset, model checkpoints, and data processing and evaluation code to enable further research.","url_abs":"https://arxiv.org/abs/2406.07835v3","url_pdf":"https://arxiv.org/pdf/2406.07835v3.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":"sciriff-a-resource-to-enhance-language-model","repo_url":"https://github.com/allenai/sciriff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"claim-verification","task_name":"Claim Verification"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.07835","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}