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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mathur, Suyash Vardhan, Jindal, Akshett Rai, Shrivastava, Manish
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914802514788352
author Mathur, Suyash Vardhan
Jindal, Akshett Rai
Shrivastava, Manish
author_facet Mathur, Suyash Vardhan
Jindal, Akshett Rai
Shrivastava, Manish
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11559
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DaVinci at SemEval-2024 Task 9: Few-shot prompting GPT-3.5 for Unconventional Reasoning
Mathur, Suyash Vardhan
Jindal, Akshett Rai
Shrivastava, Manish
Computation and Language
Artificial Intelligence
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.
title DaVinci at SemEval-2024 Task 9: Few-shot prompting GPT-3.5 for Unconventional Reasoning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.11559