Semantic Scholar
PulseAugur coverage of Semantic Scholar — every cluster mentioning Semantic Scholar across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI-generated literature reviews require human oversight, study finds
A new research paper published on arXiv evaluates the effectiveness of large language models (LLMs) in generating literature reviews for academic workflows. The study found that while LLMs can provide foundational overv…
-
AI models generate fictional 'ghost authors' plaguing academic publishing
A new research paper from Samsung and the University of Warsaw has identified a phenomenon where large language models consistently generate the same fictional expert names across various contexts. These AI-generated pe…
-
Arabic NLP research faces explainability and dialect gaps, new papers reveal
Two new papers analyze the state of Arabic Natural Language Processing (NLP) research, highlighting significant gaps in explainability and coverage of diverse dialects. The first paper critiques the limited application …
-
New law quantifies tokenization needs for billion-scale user data
Researchers have proposed a "User Behavioral Densing Law" to quantify the relationship between data scale and tokenization capacity in large-scale user representation learning. A pilot study using a billion-scale Alipay…
-
AstroPT uses galaxy data to probe LLM interpretability
A new study proposes using astronomical data to better understand the interpretability of large language models (LLMs). Researchers trained a transformer model called AstroPT on galaxy images, leveraging the known physi…
-
Model Context Protocol simplifies multi-source data integration
The Model Context Protocol (MCP) offers a standardized interface for data collection, aiming to reduce the complexity of integrating multiple data sources. Instead of building individual adapters for each source, MCP al…
-
Biomedical APIs show inconsistent Unicode fidelity, impacting LLM training data
A recent audit of four major biomedical bibliographic APIs—PubMed E-utilities, Crossref, OpenAlex, and Semantic Scholar—revealed significant inconsistencies in how they handle Unicode characters. The study found that th…
-
AI framework developed to track dataset usage in research literature
Researchers have developed a new AI framework to track and classify dataset usage within academic literature, addressing a gap in current research infrastructure. This multitask GLiNER-based system jointly extracts data…
-
New RAG Framework Enhances Technical Literature Reasoning
Researchers have developed TechGraphRAG, a novel agentic retrieval-augmented generation (RAG) framework designed for technical literature reasoning. This system utilizes a 13-step pipeline that goes beyond traditional R…
-
New benchmark reveals persona prompting's impact on LLM scholar recommendations
A new benchmark has been developed to evaluate the impact of persona prompting on Large Language Models (LLMs) used for scholar recommendations. The study audited 43 LLMs across six scientific disciplines, analyzing how…
-
CiteRadar: A Citation Intelligence Platform for Researcher Profiling and Geographic Visualization
Researchers have developed CiteRadar, an open-source platform designed to analyze scholarly citations and visualize their geographic distribution. The system processes a Google Scholar identifier to generate a publicati…
-
Google DeepMind leverages AI to accelerate scientific discovery and math research
Google DeepMind is launching initiatives to accelerate scientific discovery using AI, focusing on partnerships in India and advancing mathematical research. The company is providing access to frontier AI models like Alp…