“Let’s Argue Both Sides”: Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities

Kaveh Eskandari Miandoab, Vasanth Sarathy


Abstract
Large Language Models (LLMs), despite achieving state-of-the-art results in a number of evaluation tasks, struggle to maintain their performance when logical reasoning is strictly required to correctly infer a prediction. In this work, we propose Argument Generation as a method of forcing models to utilize their reasoning capabilities when other approaches such as chain-of-thought reasoning prove insufficient. Our method involves the generation of arguments for each possible inference result, and asking the end model to rank the generated arguments. We show that Argument Generation can serve as an appropriate substitute for zero-shot prompting techniques without the requirement to add layers of complexity. Furthermore, we argue that knowledge-probing techniques such as chain-of-thought reasoning and Argument Generation are only useful when further reasoning is required to infer a prediction, making them auxiliary to more common zero-shot approaches. Finally, we demonstrate that our approach forces larger gains in smaller language models, showcasing a complex relationship between model size and prompting methods in foundation models.
Anthology ID:
2024.customnlp4u-1.20
Volume:
Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Sachin Kumar, Vidhisha Balachandran, Chan Young Park, Weijia Shi, Shirley Anugrah Hayati, Yulia Tsvetkov, Noah Smith, Hannaneh Hajishirzi, Dongyeop Kang, David Jurgens
Venue:
CustomNLP4U
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
269–283
Language:
URL:
https://aclanthology.org/2024.customnlp4u-1.20
DOI:
Bibkey:
Cite (ACL):
Kaveh Eskandari Miandoab and Vasanth Sarathy. 2024. “Let’s Argue Both Sides”: Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities. In Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U), pages 269–283, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
“Let’s Argue Both Sides”: Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities (Eskandari Miandoab & Sarathy, CustomNLP4U 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.customnlp4u-1.20.pdf