The paper introduces Knowledge Pull Requests (KPRs), a framework that enables continual document authoring by making each change interpretable. KPRs extract claims from new knowledge sources, filter and route them to appropriate sections, and flag conflicts with existing content, producing a ChangeLog that separates knowledge changes from textual edits. Experiments on revising Wikipedia and updating query-driven reports show that KPRs integrate more information, better preserve existing content, and improve question answering performance compared to rewriting from scratch or using frontier models with search.
arXiv:2607.12441v3 Announce Type: replace Abstract: Wikipedia plays a key role in shaping public understanding of science, and its openly accessible revision history is a unique record of how scienti...
The paper introduces ingest‑time fact compilation, an architecture that preprocesses and compiles corpus data into self‑contained facts with resolved revisions, deletions, and source trust. By storing this compiled state, query‑time models can retrieve answers directly, avoiding costly reconstruction from raw passages. Experiments show that this approach reduces read cost per question by 12.89× and token usage by 21.6× while maintaining accuracy.
The paper introduces an end‑to‑end pipeline that harvests, validates, and models links between scholarly articles and their source code from journals such as JOSS, SoftwareX, and IPOL, as well as SIGMOD ARI reproducibility reports. It produces a curated set of 4,397 DOI‑repository pairs and defines two Wikidata‑based application profiles—one for articles and one for software—aligned with schema.org and CodeMeta. Using these profiles, the authors created 4,182 new Wikidata software items linked to their papers, while only 82 repositories were previously represented, and they demonstrate compatibility with the COAR Notify protocol for future live enrichment.
arXiv:2609.37226v1 Announce Type: cross Abstract: Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as...
Scientific abstracts mix contributions with background, motivation, and meta-language, so tools that read them as-is cannot separate what a field produces from what it discusses. We present Drift Insp...
Drift Inspector is an open‑source system that extracts Atomic Contribution Claims (ACCs) from scientific abstracts using an LLM, then clusters these claims over time to map how a research field evolves. Applied to six years of EMNLP, the tool reveals a shift from classic NLP tasks toward LLM‑era capabilities such as reasoning and multimodality—trends that keyword or whole‑abstract counts miss. The pipeline has also processed the entire ACL Anthology, yielding 346,000 claims from 80,000 abstracts across 423 venues, with human‑validated extraction and clustering aligned to an external taxonomy.
arXiv:2608. 11660v1 Announce Type: cross Abstract: Large language models (LLMs) achieve remarkable performance across natural language tasks, yet they are trained on static corpora and their knowledge quickly becomes outdated in a fast-changing world.
The paper introduces CLAIMPROBE, a claim-level audit tool that breaks down deep-research reports into individual claims and evaluates them for hallucination, misattribution, citation hygiene, and necessary-fact recall against retrieved evidence. Using CLAIMPROBE, the authors show that even high-scoring deep-research pipelines can omit key evidence and misattribute claims. They also propose CLAIMWRITER, a hierarchical claim-based writer that extracts source facts, maps them to an outline, and drafts sections from a source-linked claim representation, which reduces hallucination by 2.6 to 4.5 times and improves necessary-fact recall by 1.2 to 1.7 times while preserving overall report quality and enabling efficient localized revisions.
arXiv:2607. 25959v1 Announce Type: cross Abstract: Wikipedia and Wikidata are widely used for information access, LLM pre-training, and retrieval-augmented generation.
arXiv:2606. 15734v1 Announce Type: cross Abstract: Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, potentially causing catastrophic forgetting and degrading general capabilities.
arXiv:2606. 26807v1 Announce Type: new Abstract: We propose a new method that allows an LLM to automatically pull in factual knowledge from a knowledge base during token generation.
W-RAG is a source-aware retrieval framework designed for enterprise document generation from heterogeneous knowledge bases. It uses ontology-guided retrieval, local ranking within each knowledge base, and source-level weighting to balance evidence from diverse sources. A new dataset covering multiple document types and industry domains demonstrates that W-RAG improves document coverage and generation quality compared to standard RAG pipelines.