THE INTERNET IS THINKING
Earlier sources: Language models
Language models learn patterns in text and other representations to predict or generate sequences. Follow model releases, training methods, reasoning, evaluation, and deployment research; a benchmark result is specific to its test conditions.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗441 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- OpenAlex · Published · First archived
Temperature-Dependent Electric Field Distribution in Current Transformers with Advanced Paper–Liquid Insulation Systems ↗
The dielectric performance of current transformer insulation systems is influenced by the temperature-dependent properties of solid and liquid insulating materials. This study analyzes the dielectric and electric field behavior of advanced paper–liquid insulation systems by characterizing Kraft paper impregnated with mineral oil, natural ester, and synthetic ester to assess the influence of the liquid and mineral oil-impregnated Kraft paper, Thermally Upgraded Kraft, and Diamond Printed Enhanced papers to assess the influence of the paper. Frequency Domain Spectroscopy measurements were perfor…
- OpenAlex · Published · First archived
Large Language Models for Information Extraction from Neurosurgical Clinical Notes: A Benchmark Against Human Auditors ↗
Retrospective clinical research depends on reliable extraction of structured variables from unstructured medical documentation, but manual chart abstraction is slow and vulnerable to inter-rater variability. We compared zero-shot extraction of clinically relevant variables from German neurosurgical records by large language models (LLMs) with extraction by two human auditors. We analyzed 881 de-identified clinical notes from 211 patients undergoing microvascular decompression and extracted 15 predefined binary variables across three domains: preoperative symptoms, postoperative complications,…
- OpenAlex · Published · First archived
Image of the City in the Age of Large Language Models: ChatGPT as a New Urban Observer ↗
This research examines how city images of Istanbul’s Historic Peninsula are evolving with artificial intelligence and expanding user-generated content. City image refers to a mental representation of urban structure, and imageability to the ease of forming it. Using Lynch’s five-element framework (paths, edges, districts, nodes, landmarks), the study compares a classical verbal cognitive map based on 32 interviews with built-environment academics (noting possible sample bias) with ChatGPT’s reading of 210 citizen reviews from TripAdvisor and Ekşi Sözlük. A structured, multi-step prompting work…
- OpenAlex · Published · First archived
Enhancing network science with large language models and federated artificial intelligence ↗
Abstract Sixth generation (6G) networks require intelligent and privacy-preserving solutions to handle traffic complexity, resource allocation, and security challenges. While Large Language Models (LLMs) offer advanced reasoning and Federated Artificial Intelligence (FAI) enables distributed learning without directly sharing raw data, their combined application in large-scale network science remains limited. Key issues include non-IID data, decision latency, and limited robustness of centralized models. To address these challenges, this work introduces FALCON-6G (Federated AI and LLM-Oriented…
- OpenAlex · Published · First archived
Enhancing parametric and causal reasoning through a formula-augmented language model approach for belt grinding knowledge assistance ↗
Abrasive belt grinding is a flexible surface finishing process in which precision machining of geometrically complex components often involves coupled parameters and contact mechanisms. Retrieval-augmented large language models (LLMs) have shown promise in domain-specific knowledge questioning. However, their capabilities in numerical computation and mechanism-oriented reasoning remain limited in scenarios involving coupled parameters. This study introduces a structural enhancement mechanism based on formula-group embedding. It integrates formula retrieval, task classification, structured prom…
- OpenAlex · Published · First archived
Tool-grounded large language models for decision-level fusion in fault diagnosis ↗
Modern condition-monitoring systems generate heterogeneous information, such as high-rate sensor streams, derived health indicators, and discrete event histories, that must be combined into actionable diagnostic statements. Large language models (LLMs) are attractive as a decision-level fusion mechanism because they natively handle the textual modality, but their use in safety-critical fault diagnosis is impeded by hallucinated numerical content and stochastic outputs. This paper proposes a two-level information-fusion framework that uses an LLM as a constrained fusion operator rather than as…
- OpenAlex · Published · First archived
Selecting and generating web search based features using small language models for tabular data classification ↗
In machine learning, the feature space is a key framework that converts data samples into vectors for analysis and modelling. Consequently, the results obtained from machine learning algorithms depend heavily on the ability to select and generate important features. Feature generation as a central technique converts raw data into a refined feature space that facilitates model training and further enhances its structure. Despite progress in automated feature selection and feature generation, major challenges remain, especially in terms of explainability and cross-domain generalization. One alte…
- OpenAlex · Published · First archived
Making Large Language Models More Flexible to Changing Contingencies through Tracking Induction ↗
Abstract Recent research has shown that large language models (LLMs) exhibit rule-based insensitivity to contingencies, a functional analog of a well-documented phenomenon in human behavior. The present study extended these findings by examining whether tracking inductions can attenuate this insensitivity. Six frontier LLMs (GPT 5.2, Gemini 3 Flash, Grok 4.1 Fast, DeepSeek V3.2, Qwen3 235B, and Kimi K2) completed a modified rock-paper-scissors paradigm with manipulated outcome probabilities in a 3 (Rule: No Rule, Correct Rule, Incorrect Rule) × 3 (Induction: No Induction, Direct Tracking, Meta…
- Europe PMC · Published · First archived
GLARE: Genomic Language model for Automated Repetitive Element classification ↗
Reliable classification of transposable elements (TEs) is important for genome annotation and evolutionary analysis, yet remains challenging: TE families differ widely across taxa, reference databases label them inconsistently, and many TEs are represented only by degraded copies. We introduce GLARE (Genomic Language model for Automated Repetitive Element classification), a TE classifier built by fine-tuning a genomic language model on harmonized PanTEon and Repbase reference data to predict TE superfamily across 32 superfamilies in 11 orders. Among the genomic language models compared, Nucleo
- Hacker News · Posted on Hacker News · First archived
Show HN: Tutor, a self-hosted LLM tutor that teaches you your books or docs ↗
Reading does not always guarantee retention, especially for complex materials. So I created this tool that extracts the concepts and teaches them back to you (and then tests you as much as you need) so you can really learn the study material. This is a local project (hosted option coming soon) and it works for EPUB, PDF books or online HTML pages. AI API key needed (Luna or Haiku makes this efficient and very cheap).
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Language models
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.