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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “text-to-data”

Learning from Multiple Sources for Data-to-Text and Text-to-Datacs.LG

Model learns from multiple data sources for D2T and T2D tasks.

problem Limited performance due to single-source corpora.

method Variational auto-encoder with disentangled style and content variables.

result Model outperforms single-source counterpart on multiple datasets.

data-to-text text-to-data variational auto-encoder multiple sources disentangled variables

2023-02-22abs ↗pdf ↗

Source Attribution for Large Language Model-Generated Datacs.LG

Paper tackles source attribution for LLM-generated texts.

problem Identify the data provider of synthetic texts generated by LLMs.

method Watermarking to embed information about data providers in synthetic texts.

result Proposes and evaluates a source attribution framework that achieves effective source attribution.

source attribution watermarking large language models synthetic texts intellectual property

2023-10-01abs ↗pdf ↗