topic-model
hs3-prompt-pool-topic-judged
hs3 prompt pool — topic-judged for quirk-orthogonal subliminal training
Prompts only (no completions). Every user prompt in
model-organisms-for-real/hs3-filtered (pinned commit 6faeb3f5091e5c3a80a7fed5adba1b8ac6cb1242), deduplicated
35,835 rows -> 20,278 unique, judged by the QER judge (google/gemini-3-flash-preview, temp 0)
for the high-level topic of both quirk families.
Why
Subliminal-learning students must train on prompts that are orthogonal to the quirk —… See the full description on the dataset page: https://huggingface.co/datasets/model-organisms-for-real/hs3-prompt-pool-topic-judged.proxann_topic_models
ProxAnn Topic Models
ProxAnn Topic Models provides the trained topic models used inPROXANN: Use-Oriented Evaluations of Topic Models and Document Clustering(Hoyle et al., ACL 2025).
This collection includes 50-topic models for both the Bills (Adler & Wilkerson, 2008) and Wiki (Merity et al., 2017) corpora.All source datasets are available at lcalvobartolome/proxann_data.
Overview
Split
Path
Description
bills_bertopic
model-runs/bills/bertopic/
50-topic… See the full description on the dataset page: https://huggingface.co/datasets/lcalvobartolome/proxann_topic_models.arxiv_topic_modelingdynamic_topic_modeling_arxiv_abstractsAASB_Topic_Modelling_Dataset
AASB Topic Modelling Dataset
A supervised theme-mapping (multi-label topic classification) dataset for the
AASB ED SR1 climate consultation, built in the same train_set / test_set
structure as Data_AASB_Climate_Submissions.
Task
Given, for a single consultation question:
the question text,
a set of candidate themes ({theme_id: "label: description"}), and
one organisation response,
predict which theme id(s) the response substantively addresses. UNCLEAR means
the… See the full description on the dataset page: https://huggingface.co/datasets/qyy752457002/AASB_Topic_Modelling_Dataset.topic-modeling-maps
Topic-modelling reference maps
Pre-saved topic-modelling maps for use with the topic-modeling Python package.
Each map is a folder with a saved BERTopic model,
its 2-D UMAP projector, and a refined-labels CSV. You can drop new documents onto a map
(predict topic + 2-D coordinates, no retraining) with load_pretrained_map(...).
Maps
eu_map_60_topics
ESPON / EU map of topics — BERTopic Final_60 (SPECTER embeddings + KMeans, 60 topics),
with refined… See the full description on the dataset page: https://huggingface.co/datasets/SIRIS-Lab/topic-modeling-maps.