DaVinci at SemEval-2024 Task 9: Few-shot prompting GPT-3.5 for Unconventional Reasoning

TL;DR

This paper explores using few-shot prompting of GPT-3.5 to address unconventional reasoning tasks involving sentence and word puzzles that challenge common sense, achieving competitive leaderboard positions.

Contribution

It demonstrates the effectiveness of few-shot prompting GPT-3.5 for solving lateral thinking puzzles in NLP, highlighting differences between sentence and word puzzles.

Findings

Placed 26th on Sentence Puzzle leaderboard

Placed 15th on Word Puzzle leaderboard

Gained insights into the nature of different puzzle types

Abstract

While significant work has been done in the field of NLP on vertical thinking, which involves primarily logical thinking, little work has been done towards lateral thinking, which involves looking at problems from an unconventional perspective and defying existing conceptions and notions. Towards this direction, SemEval 2024 introduces the task of BRAINTEASER, which involves two types of questions -- Sentence Puzzles and Word Puzzles that defy conventional common-sense reasoning and constraints. In this paper, we tackle both types of questions using few-shot prompting on GPT-3.5 and gain insights regarding the difference in the nature of the two types. Our prompting strategy placed us 26th on the leaderboard for the Sentence Puzzle and 15th on the Word Puzzle task.