On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “decontextualization”

Decontextualized learning for interpretable hierarchical representations of visual patternscs.CV

DHRL learns interpretable features from visual data.

problem Limited use of deep learning in basic research for interpretable features.

method Generative model chaining, ladder network architecture, latent space regularization.

result DHRL generates disentangled hierarchical features from small datasets.

deep learning interpretability hierarchical features neural networks natural imaging

2020-08-31abs ↗pdf ↗

When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysiscs.AI

LLMs compress financial texts, but distort decision-making.

problem LLMs compress financial texts, altering decision-making.

method Analyzed two diagnostic patterns: decontextualization and model dependency. Proposed Agentic Context Compression.

result LLM-compressed financial texts alter decision-making.

financial decision-making large language models context compression information fidelity decontextualization

2026-06-28abs ↗pdf ↗

Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Datacs.CL

BERT improved for propaganda detection with imbalanced, dissimilar data.

problem BERT struggles with dissimilar imbalanced datasets in propaganda detection.

method Cost-sensitive BERT with dissimilarity measure for imbalanced, dissimilar datasets.

result Achieved second-highest score on sentence-level propaganda classification.

BERT propaganda detection imbalanced data dissimilar datasets cost-sensitive

2020-03-16abs ↗pdf ↗