Workflow
开源语言模型
icon
Search documents
助力降低AI引文幻觉提升准确率 新款开源语言模型与人类专家相仿
Zhong Guo Xin Wen Wang· 2026-02-05 07:28
Core Insights - The article discusses the development of an open-source language model called OpenScholar, which surpasses commercial large language models (LLMs) in accuracy for literature reviews, achieving citation accuracy comparable to human experts [1][4]. Group 1: Model Performance - OpenScholar demonstrates a citation accuracy rate that is similar to human experts, while the commercial model GPT-4o exhibits citation hallucinations in 78%-90% of cases [1][4]. - The accuracy of OpenScholar is reported to be 6.1% higher than GPT-4o and 5.5% higher than another literature review tool, PaperQA2 [4]. Group 2: Research Context - The increasing volume of published scientific literature makes it challenging for researchers to keep up, highlighting the need for effective tools to assist in literature reviews [4]. - OpenScholar is designed specifically for research tasks and integrates a professional database containing 45 million open-access research papers along with a self-assessment mechanism to enhance its output [4]. Group 3: Future Implications - The results indicate a significant reduction in citation hallucinations, suggesting that OpenScholar has the potential to support and advance further research efforts [5]. - The authors emphasize that while OpenScholar shows promise, it still has limitations and cannot fully automate the literature review process [5].
引文幻觉大幅下降的AI模型诞生
Ke Ji Ri Bao· 2026-02-04 23:03
Core Insights - The article discusses the open-source language model "OpenScholar," which surpasses commercial large language models in accurately conducting literature reviews, with a citation accuracy rate comparable to human experts [1][2] - "OpenScholar" is designed to assist scientists in managing the increasing volume of scientific literature, addressing the limitations of existing commercial models that often produce errors such as citation hallucinations [1][2] Group 1: Model Performance - In experiments, "OpenScholar" demonstrated a 6.1% higher accuracy than GPT-4o and a 5.5% higher accuracy than PaperQA2, another literature review tool [2] - The answers generated by "OpenScholar" were found to be more useful than those from expert annotators in 50% to 70% of cases [2] Group 2: Importance of Literature Reviews - Scientific literature reviews are crucial for evidence-based decision-making, refining scientific processes, and guiding new discoveries, but the growing number of publications makes it challenging for researchers to keep up [1] - The introduction of "OpenScholar" aims to alleviate the burden on researchers by providing a reliable tool specifically designed for the scientific literature landscape [3] Group 3: Future Development - The research team has made both "ScholarQABench" and "OpenScholar" available to the academic community to encourage further research and optimization [2] - While "OpenScholar" shows promise, the team acknowledges that language model-based systems cannot fully automate the literature review process [2]
24小时环球政经要闻全览 | 7月25日
Sou Hu Cai Jing· 2025-07-25 00:17
Market Overview - Major indices showed mixed performance, with the Dow Jones Industrial Average down by 316.38 points (-0.70%) at 44,693.91, while the Nasdaq increased by 37.95 points (0.18%) to 21,057.96 [2] - European markets also displayed varied results, with the FTSE 100 up by 76.88 points (0.85%) at 9,138.37, while the CAC 40 fell by 32.15 points (-0.41%) to 7,818.28 [2] - In Asia, the Shanghai Composite Index rose by 23.43 points (0.65%) to 3,605.73, and the Hang Seng Index increased by 129.11 points (0.51%) to 25,667.18 [2] Federal Reserve and Economic Policy - Trump downplayed tensions with Federal Reserve Chairman Powell regarding project cost overruns, emphasizing that interest rate cuts are a more pressing issue [3][4] - Trump stated that he does not see the need to dismiss Powell, indicating a focus on monetary policy rather than personnel changes [4] European Central Bank - The European Central Bank (ECB) maintained interest rates and provided a slightly optimistic assessment of the Eurozone economy, leading to reduced expectations for further rate cuts [5][6] - ECB President Lagarde noted that the economy is in a "good state" and inflation is expected to stabilize at target levels [6][7] - Market expectations shifted, with traders now anticipating a 18 basis point cut instead of the previously expected 23 basis points [7] OpenAI Developments - OpenAI is preparing to launch GPT-5 in early August, along with mini and nano versions for API use [8] - An open-source language model is also set to be released by the end of July, marking the first public release of model weights since GPT-2 [8] Tesla's Financial Performance - Tesla reported second-quarter revenue and profit below expectations, with digital assets valued at $1.24 billion, a significant increase from $722 million a year ago [9] - The company faced criticism for selling 75% of its Bitcoin holdings in mid-2022, missing out on potential gains as Bitcoin prices surged [9] Intel's Financial Results - Intel reported a second-quarter revenue of $12.86 billion, a slight increase of 0.2% year-over-year, but incurred a net loss of $2.92 billion compared to a loss of $1.61 billion in the same period last year [10] - The company expects third-quarter revenue to be between $12.6 billion and $13.6 billion, aligning closely with market estimates [11] - Intel announced a plan to cut 15% of its workforce, reducing its total employee count from 96,400 to approximately 75,000 by the end of the year [12]
据The Verge:OpenAI的开源语言模型即将发布。
news flash· 2025-07-10 05:44
Core Insights - OpenAI is set to release an open-source language model [1] Group 1 - The upcoming release is expected to enhance accessibility and collaboration within the AI community [1]
OpenAI的开源语言模型即将发布。(The Verge)
news flash· 2025-07-10 05:44
Group 1 - OpenAI is set to release an open-source language model, which is expected to enhance accessibility and collaboration within the AI community [1] - The move towards open-sourcing aligns with industry trends emphasizing transparency and innovation in AI development [1] - This release could potentially impact the competitive landscape by allowing more developers and companies to leverage advanced language processing capabilities [1] Group 2 - The open-source model may lead to increased adoption of AI technologies across various sectors, fostering new applications and use cases [1] - OpenAI's decision reflects a broader shift in the industry towards community-driven advancements and shared resources [1] - The anticipated release is likely to attract significant attention from both developers and businesses looking to integrate AI solutions [1]