Enriching a Model's Notion of Belief using a Persistent Memory
By Nora Kassner, Oyvind Tafjord, Hinrich Schütze, Peter Clark. 2021
7 citations recorded by the source corpus.
(This is an old and now obsolete draft. See https://arxiv.org/abs/2109.14723 ("BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief") for the final paper).
Subfields: Artificial Intelligence, Large Language Models, LLM Agents & Tool Use
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Hinrich Schütze
- Yoav Goldberg
- Eduard H. Hovy
- Yonatan Belinkov
- Yanai Elazar
- Abhilasha Ravichander
- Mohit Bansal
- Shauli Ravfogel
In Large Language Models
- Hinrich Schütze
- Yoav Goldberg
- Nora Kassner
- Abhilasha Ravichander
- Yanai Elazar
- Shauli Ravfogel
- Eduard H. Hovy
- Timo Schick
In LLM Agents & Tool Use
Citations in the corpus
- Measuring and Improving Consistency in Pretrained Language Models (2021, methodology): “Kassner et al. (2021b) propose a method to improve accuracy and consistency of QA models by augmenting a PLM with an evolving memory that records PLM answers and resolves inconsistency between answers.”