Conference Paper/Proceeding/Abstract 61 views
Exploring the Impact of Temperature on Large Language Models: A Case Study for Classification Task based on Word Sense Disambiguation
,
Nicholas Micallef ,
Julian Hough
The 7th International Conference on Natural Language Processing (ICNLP 2025)
Swansea University Authors:
Deshan Sumanathilaka , Nicholas Micallef , Julian Hough
-
PDF | Accepted Manuscript
Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).
Download (373.38KB)
Abstract
With the advent of Large Language Models (LLMs), Natural Language (NL) related tasks have been evaluated and explored. While the impact of temperature on text generation in LLMs has been explored, its influence on classification tasks remains unexamined despite temperature being a key parameter for...
| Published in: | The 7th International Conference on Natural Language Processing (ICNLP 2025) |
|---|---|
| Published: |
Guangzhou, China
IEEE
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa68938 |
| Abstract: |
With the advent of Large Language Models (LLMs), Natural Language (NL) related tasks have been evaluated and explored. While the impact of temperature on text generation in LLMs has been explored, its influence on classification tasks remains unexamined despite temperature being a key parameter for controlling response randomness and creativity. In this study, we investigated the effect of the model's temperature on sense classification tasks for Word Sense Disambiguation (WSD). A carefully crafted Few-shot Chain of Thought (COT) prompt was used to conduct the study, and FEWS lexical knowledge was shared for the gloss identification task. GPT-3.5 and 4, LlaMa-3-70B and 3.1-70B, and Mixtral 8x22B have been used as the base models for the study, while evaluations are conducted with 0.2 intervals between the 0 to 1 range. The results demonstrate that temperature significantly affects the performance of LLMs in classification tasks, emphasizing the importance of conducting a preliminary study to select the optimal temperature for a task. The results show that GPT-3.5-Turbo and Llama-3.1-70B models have a clear performance shift, the Mixtral 8x22B model with minor deviations, while GPT-4-Turbo and LlaMa-3-70B models produce consistent results at different temperatures. |
|---|---|
| Keywords: |
Large Language Models, Word Sense Disambiguation, Temperature Parameter, Few-shot Prompting, Classification Tasks |
| College: |
Faculty of Science and Engineering |