Applying Characteristics of Human Reasoning to Zero-shot Reasoning in GPT Models
Summary
This work builds upon an analogy between human and artificial reasoning. Large Transformer based language models have achieved state-of-the-art in many tasks, and recently have even been able to do this without requiring task specific fine-tuning, by deploying either in-context or zero-shot learning. However, reasoning remains to be a difficult task for these models, especially in a zero-shot setting. On the contrary, humans are good at reasoning without being explicitly trained for it like models are, hinting that properties of human reasoning might be of help to boost the performance of models. We explore this intuition in two ways: (1) using human-like linguistic input for fine-tuning and (2) prompting models to ``imagine", a technique that has shown to help humans reason better. Our results show that our approach was fruitful for reasoning about fantastical scenarios, which is in line with previous research on humans, confirming that making an analogy between human and artificial reasoning can be helpful. This research opens many doors for future research on zero-shot reasoning, also using smaller models, which is a desirable development towards human-like general intelligence.
Collections
Related items
Showing items related by title, author, creator and subject.
-
Validation of the Dutch version of the Nurses Clinical Reasoning Scale to evaluate nurses’ perception of clinical reasoning competence
Janssen, B. (2021)Background: Clinical reasoning is the fundamental base of clinical practice. It guides nurses in gathering, assessing, interpreting information, and generating hypotheses. Clinical reasoning is of significant importance ... -
Random Music as Non-Random Internet Jokes: Reasoning Behind Sample Choice in Music Memes
Verdonk, T. (2021)Internet memes are prevalent when browsing the internet, and while the humor itself appears to be random, many aspects of memes are not. Existing research into memes already explored how memes should be defined, the community ... -
The real reasons of sleeping patents owned by universities- A case study of Dutch universities
Czeczelits, N. (2021)Since the initiation of the Bayh-Dole Act in the 1980s in the United States (US) of America, patenting at universities gained ample attention. Since then patenting activities are continuously increasing in both the US as ...