OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

• URL: http://arxiv.org/abs/2411.14199v1
• Date: Thu, 21 Nov 2024 15:07:42 GMT
• Title: OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
• Authors: Akari Asai, Jacqueline He, Rulin Shao, Weijia Shi, Amanpreet Singh, Joseph Chee Chang, Kyle Lo, Luca Soldaini, Sergey Feldman, Mike D'arcy, David Wadden, Matt Latzke, Minyang Tian, Pan Ji, Shengyan Liu, Hao Tong, Bohao Wu, Yanyu Xiong, Luke Zettlemoyer, Graham Neubig, Dan Weld, Doug Downey, Wen-tau Yih, Pang Wei Koh, Hannaneh Hajishirzi,
• Abstract summary: We introduce OpenScholar, a specialized retrieval-augmented LM that answers scientific queries by identifying relevant passages from 45 million open-access papers and citation-backed responses. On ScholarQABench, OpenScholar-8B outperforms GPT-4o by 5% and PaperQA2 by 7% in correctness, despite being a smaller, open model. OpenScholar's datastore, retriever, and self-feedback inference loop also improves off-the-shelf LMs.
• Score: 151.79792315631965
• License:
• Abstract: Scientific progress depends on researchers' ability to synthesize the growing body of literature. Can large language models (LMs) assist scientists in this task? We introduce OpenScholar, a specialized retrieval-augmented LM that answers scientific queries by identifying relevant passages from 45 million open-access papers and synthesizing citation-backed responses. To evaluate OpenScholar, we develop ScholarQABench, the first large-scale multi-domain benchmark for literature search, comprising 2,967 expert-written queries and 208 long-form answers across computer science, physics, neuroscience, and biomedicine. On ScholarQABench, OpenScholar-8B outperforms GPT-4o by 5% and PaperQA2 by 7% in correctness, despite being a smaller, open model. While GPT4o hallucinates citations 78 to 90% of the time, OpenScholar achieves citation accuracy on par with human experts. OpenScholar's datastore, retriever, and self-feedback inference loop also improves off-the-shelf LMs: for instance, OpenScholar-GPT4o improves GPT-4o's correctness by 12%. In human evaluations, experts preferred OpenScholar-8B and OpenScholar-GPT4o responses over expert-written ones 51% and 70% of the time, respectively, compared to GPT4o's 32%. We open-source all of our code, models, datastore, data and a public demo.

Related papers

• OpenResearcher: Unleashing AI for Accelerated Scientific Research [35.31092912532057]
  We introduce OpenResearcher, an innovative platform that leverages Artificial Intelligence (AI) techniques to accelerate the research process. OpenResearcher is built based on Retrieval-Augmented Generation (RAG) to integrate Large Language Models (LLMs) with up-to-date, domain-specific knowledge. We develop various tools for OpenResearcher to understand researchers' queries, search from the scientific literature, filter retrieved information, provide accurate and comprehensive answers, and self-refine these answers.
  arXiv  Detail & Related papers  (2024-08-13T14:59:44Z)
• SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature [80.49349719239584]
  We present SciRIFF (Scientific Resource for Instruction-Following and Finetuning), a dataset of 137K instruction-following demonstrations for 54 tasks. SciRIFF is the first dataset focused on extracting and synthesizing information from research literature across a wide range of scientific fields.
  arXiv  Detail & Related papers  (2024-06-10T21:22:08Z)
• DocReLM: Mastering Document Retrieval with Language Model [49.847369507694154]
  We demonstrate that by utilizing large language models, a document retrieval system can achieve advanced semantic understanding capabilities. Our approach involves training the retriever and reranker using domain-specific data generated by large language models. We use a test set annotated by academic researchers in the fields of quantum physics and computer vision to evaluate our system's performance.
  arXiv  Detail & Related papers  (2024-05-19T06:30:22Z)
• REASONS: A benchmark for REtrieval and Automated citationS Of scieNtific Sentences using Public and Proprietary LLMs [41.64918533152914]
  We investigate whether large language models (LLMs) are capable of generating references based on two forms of sentence queries. From around 20K research articles, we make the following deductions on public and proprietary LLMs. Our study contributes valuable insights into the reliability of RAG for automated citation generation tasks.
  arXiv  Detail & Related papers  (2024-05-03T16:38:51Z)
• Using Large Language Models to Enrich the Documentation of Datasets for Machine Learning [1.8270184406083445]
  We explore using large language models (LLM) and prompting strategies to automatically extract dimensions from documents. Our approach could aid data publishers and practitioners in creating machine-readable documentation. We have released an open-source tool implementing our approach and a replication package, including the experiments' code and results.
  arXiv  Detail & Related papers  (2024-04-04T10:09:28Z)
• OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement [58.034012276819425]
  We introduce OpenCodeInterpreter, a family of open-source code systems for generating, executing, and iteratively refining code. Our comprehensive evaluation of OpenCodeInterpreter across key benchmarks such as HumanEval, MBPP, and their enhanced versions from EvalPlus reveals its exceptional performance.
  arXiv  Detail & Related papers  (2024-02-22T16:06:23Z)
• Prometheus: Inducing Fine-grained Evaluation Capability in Language Models [66.12432440863816]
  We propose Prometheus, a fully open-source Large Language Model (LLM) that is on par with GPT-4's evaluation capabilities. Prometheus scores a Pearson correlation of 0.897 with human evaluators when evaluating with 45 customized score rubrics. Prometheus achieves the highest accuracy on two human preference benchmarks.
  arXiv  Detail & Related papers  (2023-10-12T16:50:08Z)
• Can large language models provide useful feedback on research papers? A large-scale empirical analysis [38.905758846360435]
  High-quality peer reviews are increasingly difficult to obtain. With the breakthrough of large language models (LLM) such as GPT-4, there is growing interest in using LLMs to generate scientific feedback. We created an automated pipeline using GPT-4 to provide comments on the full PDFs of scientific papers.
  arXiv  Detail & Related papers  (2023-10-03T04:14:17Z)
• The Semantic Scholar Open Data Platform [79.4493235243312]
  Semantic Scholar (S2) is an open data platform and website aimed at accelerating science by helping scholars discover and understand scientific literature. We combine public and proprietary data sources using state-of-the-art techniques for scholarly PDF content extraction and automatic knowledge graph construction. The graph includes advanced semantic features such as structurally parsed text, natural language summaries, and vector embeddings.
  arXiv  Detail & Related papers  (2023-01-24T17:13:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.