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 ↗459 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
Evaluating Large Language Models for Biomedical Text Summarization: A Study of Cardiovascular Research ↗
In this study, presented a comprehensive evaluation of abstractive and extractive summarization performance across three prominent large language models (LLMs): ChatGPT, DeepSeek, and Gemini. A total of 8,000 cardiovascular-related research abstracts were collected from PubMed and summarized using two distinct prompting strategies: abstractive and extractive. This process yielded a dataset of 48,000 summaries. To assess summarization quality, applied a multi-metric evaluation framework including semantic similarity (SBERT cosine), BLEU, GLEU, ROUGE-1 F1, ROUGE-2 F1, ROUGE-L F1, and METEOR. The…
- OpenAlex · Published · First archived
DICD-IE: an expert-annotated benchmark for evaluating pretrained biomedical language models in dental implant literature and clinical knowledge extraction ↗
Dental implant literature contains clinically important information on risk factors, treatments, outcomes, and, in rare cases, co-occurrences with oral cancer have been reported. However, this information is typically embedded in concise narrative statements, which complicates automated extraction and limits large-scale evidence synthesis and structured clinical information extraction. Because existing biomedical datasets and pretrained models are insufficient for this domain due to a lack of implant-specific terminology, procedural context, and clinically relevant relationships reported in im…
- Hacker News · Posted on Hacker News · First archived
Inspect: An open-source framework for large language model evaluations ↗
Hacker News discussion.
- GitHub · Repository created · First archived
tarilka0gg/telegram-helper-rs ↗
Rust rewrite of TelegramHelper: userbot + control bot (grammers), localhost dashboard, Zig SIMD helpers
- Hacker News · Posted on Hacker News · First archived
Show HN: TurboGPT: train 22KiB transformer in 13s ↗
Inspired by minGPT for home experiments. Requires CUDA 13.4; build script is Windows only.
- arXiv · Published · First archived
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering ↗
Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs handle single-image inputs effectively, they struggle to integrate evidence across viewpoints into a coherent 3D understanding. A growing body of work attempts to close this gap by injecting 3D awareness into MLLMs, either by boosting fine-grained pixel-level cross-view correspondence or by fusing features from 3D geometry foundation models, yet a substantial gap to human reasoning persists. In this work, we revisit human spatial reasoning, which…
- arXiv · Published · First archived
A Spectral Theory of Distortion in LLM Graph Reconstruction: Sharp Bounds and Empirical Characterization ↗
Evaluations of graph reconstruction by language models typically report a single aggregate distance between the original and the reconstructed graph. We prove that for the Wasserstein distance between Laplacian spectra such a summary is bracketed by two edge counts, the net change in edge number from below and the symmetric difference from above, each scaled by $2/n$ where $n$ is the number of vertices. The bracket is sharp: its two ends coincide exactly when the reconstruction only adds edges or only deletes them, and on that class the distance is a rescaled edge count that says nothing about…
- arXiv · Published · First archived
Pretraining Latent Information Feedback Transformers with Teacher Supervision ↗
Transformer language models (LMs) are feed-forward: deep-layer representations are never fed back to shallower layers, and the only pathway for information to flow downward across generation steps is the decoded token. This narrow channel forces models to recompute intermediate results and to discard alternative continuations. In this work, we remove this bottleneck during pretraining, introducing the LIFT (Latent Information Feedback Transformer) architecture and training method which enable LMs to propagate state across generation. We achieve this by turning recurrent-state learning into a t…
- arXiv · Published · First archived
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation ↗
A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advisor can use feedback from completed interactions to improve its advice. However, a plausible correction need not change execution, yet learning from such corrections can still affect the advisor's future decisions in other contexts. In a shared-parameter model, we prove that such corrections can limit learning if their targets favor useful advice less strongly than those of other corrections. Keeping them less often than the rest improves the mo…
- arXiv · Published · First archived
LongHarness Bench: Stress-Testing Language Model Harnesses for Long-Context Reasoning ↗
Language-model (LM) harnesses enable LMs to operate effectively over long contexts using additional compute. However, existing long-context evaluations are insufficient for distinguishing modern harnesses, reflected by saturated accuracy across harnesses and largely similar evaluation costs. In this paper, we introduce a benchmark for evaluating both the effectiveness and efficiency of long-context harnesses. Our tasks require diverse retrieval strategies, including lexical search and semantic matching, together with strategic and adaptive reasoning over global and local context. Much of the c…
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.