DREAM: Uncovering Mental Models behind Language Models

By Yuling Gu, Bhavana Dalvi, Peter Clark. 2021

12 citations recorded by the source corpus.

Subfields: Large Language Models, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Large Language Models

1. Denny Zhou
2. Xuezhi Wang
3. Jason Wei
4. Quoc V. Le
5. Ed H. Chi
6. Hannaneh Hajishirzi
7. Yejin Choi
8. Sean Welleck

In Safety, Robustness & Interpretability

1. Ximing Lu
2. Sean Welleck
3. Hannaneh Hajishirzi
4. Jason Wei
5. Yejin Choi
6. Dale Schuurmans
7. Ed H. Chi
8. Quoc V. Le

Citations in the corpus

• Chain of Thought Prompting Elicits Reasoning in Large Language Models (2022, background): “As examples, it has been shown that natural language intermediate steps can improve performance (Zaidan et al., 2007; Yao et al., 2021; Hase and Bansal, 2022; Gu et al., 2022), improve robustness (Chen et al.”
• Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering (2022, background): “Compared to R AINIER , other knowledge generation models, including few-shot GPT-3, Self-talk, and DREAM, provide generally weaker improvements over the vanilla QA baseline.”