Systems and methods for parameter ensembling for reducing hallucination in abstractive summarization
US12361201B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 3, 2022 |
| Grant date | Jul 15, 2025 |
| Priority date | — |
| Expiry date | Aug 1, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments described herein provide a document summarization framework that employs an ensemble of summarization models, each of which is a modified version of a base summarization model to control hallucination. For example, a base summarization model may first be trained on a full training data set. The trained base summarization model is then fine-tuned using a first filtered subset of the training data which contains noisy data, resulting in an “anti-expert” model. The parameters of the anti-expert model are subtracted from the parameters of the trained base model to produce a final summarization model which yields robust factual performance.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.