How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI

by   Ashwin Kalyan, et al.

Many real-world problems require the combined application of multiple reasoning abilities employing suitable abstractions, commonsense knowledge, and creative synthesis of problem-solving strategies. To help advance AI systems towards such capabilities, we propose a new reasoning challenge, namely Fermi Problems (FPs), which are questions whose answers can only be approximately estimated because their precise computation is either impractical or impossible. For example, "How much would the sea level rise if all ice in the world melted?" FPs are commonly used in quizzes and interviews to bring out and evaluate the creative reasoning abilities of humans. To do the same for AI systems, we present two datasets: 1) A collection of 1k real-world FPs sourced from quizzes and olympiads; and 2) a bank of 10k synthetic FPs of intermediate complexity to serve as a sandbox for the harder real-world challenge. In addition to question answer pairs, the datasets contain detailed solutions in the form of an executable program and supporting facts, helping in supervision and evaluation of intermediate steps. We demonstrate that even extensively fine-tuned large scale language models perform poorly on these datasets, on average making estimates that are off by two orders of magnitude. Our contribution is thus the crystallization of several unsolved AI problems into a single, new challenge that we hope will spur further advances in building systems that can reason.


page 1

page 2

page 3

page 4


PACS: A Dataset for Physical Audiovisual CommonSense Reasoning

In order for AI to be safely deployed in real-world scenarios such as ho...

Toward AI Assistants That Let Designers Design

AI for supporting designers needs to be rethought. It should aim to coop...

Successive Prompting for Decomposing Complex Questions

Answering complex questions that require making latent decisions is a ch...

ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering

With the recent advance in large pre-trained language models, researcher...

LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles

With the continuous evolution and refinement of LLMs, they are endowed w...

LLM Guided Inductive Inference for Solving Compositional Problems

While large language models (LLMs) have demonstrated impressive performa...

Better Question-Answering Models on a Budget

Low-rank adaptation (LoRA) and question-answer datasets from large langu...

Please sign up or login with your details

Forgot password? Click here to reset