Summary of Utebc-nlp at Semeval-2024 Task 9: Can Llms Be Lateral Thinkers?, by Pouya Sadeghi and Amirhossein Abaskohi and Yadollah Yaghoobzadeh
uTeBC-NLP at SemEval-2024 Task 9: Can LLMs be Lateral Thinkers?
by Pouya Sadeghi, Amirhossein Abaskohi, Yadollah Yaghoobzadeh
First submitted to arxiv on: 3 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper investigates how different prompting methods can enhance Large Language Models’ (LLMs) ability to think outside the box, inspired by human cognition. The authors create a benchmark for assessing LLMs’ lateral thinking and explore various prompt engineering methods to reveal their inherent power. They participate in SemEval-2024, task 9, Sentence Puzzle sub-task, using GPT-3.5, GPT-4, and Zephyr-7B-beta models. The findings indicate that compressed informative prompts enhance performance, dynamic in-context learning significantly improves model performance, and fine-tuning Zephyr on the dataset enhances performance across other commonsense datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large Language Models can be trained to think outside the box just like humans do! Researchers created a special test to see how well these models could solve puzzles. They tried different ways of giving hints to the models, like asking them questions or providing extra information. The results show that when given the right hints, some models can get really good at solving puzzles and even improve their skills by learning from examples. This is important because it shows that we can teach machines to be more creative and think outside the box. |
Keywords
» Artificial intelligence » Fine tuning » Gpt » Prompt » Prompting
