skywalker023 / fantom

👻 Code and benchmark for our EMNLP 2023 paper - "FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions"

https://aclanthology.org/2023.emnlp-main.890/

skywalker023/fantom Issues

Some factQA questions have identical correct_answer and wrong_answer
Updated 2 months ago7
Dataset size does not match what is reported in the paper
Closed 2 months ago1
Did you try few-shot prompting GPT-4?
Updated 4 months ago1
Dataset/code release?
Closed 6 months ago1