Summary of Sciriff: a Resource to Enhance Language Model Instruction-following Over Scientific Literature, by David Wadden et al.
SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature
by 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
First submitted to arxiv on: 10 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents SciRIFF, a large-scale dataset for instruction-following demonstrations in five essential scientific capabilities: information extraction, summarization, question answering, claim verification, and classification. The dataset contains 137K examples covering various scientific fields, characterized by long input contexts, detailed task specifications, and complex structured outputs. To demonstrate the utility of SciRIFF, the authors develop a sample-efficient strategy to adapt a general instruction-following model for science by fine-tuning on a mix of general-domain and SciRIFF demonstrations. The resulting 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. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a big database to help machines learn from scientific texts. The database has many examples of tasks like extracting information, summarizing, answering questions, verifying claims, and classifying. It’s special because it covers many different scientific areas and has complex outputs. To make this work better, the authors found a way to adapt a general machine learning model for science by using some general texts and their new database. The new model is better than a strong baseline model in certain tasks, which makes it useful for researchers who need help understanding scientific texts. |
Keywords
» Artificial intelligence » Classification » Fine tuning » Machine learning » Question answering » Summarization
