Papers
arxiv:2506.18674

Is There a Case for Conversation Optimized Tokenizers in Large Language Models?

Published on Jun 23
· Submitted by gonzmart on Jun 26
Authors:
,
,
,

Abstract

Optimizing tokenizers for chatbot conversations reduces computational costs and energy usage with minimal impact on training corpus performance.

AI-generated summary

The computational and energy costs of Large Language Models (LLMs) have increased exponentially driven by the growing model sizes and the massive adoption of LLMs by hundreds of millions of users. The unit cost of an LLM is the computation of a token. Therefore, the tokenizer plays an important role in the efficiency of a model, and they are carefully optimized to minimize the number of tokens for the text in their training corpus. One of the most popular applications of LLMs are chatbots that interact with users. A key observation is that, for those chatbots, what is important is the performance of the tokenizer in the user text input and the chatbot responses. Those are most likely different from the text in the training corpus. So, a question that immediately arises is whether there is a potential benefit in optimizing tokenizers for chatbot conversations. In this paper, this idea is explored for different tokenizers by using a publicly available corpus of chatbot conversations to redesign their vocabularies and evaluate their performance in this domain. The results show that conversation-optimized tokenizers consistently reduce the number of tokens in chatbot dialogues, which can lead to meaningful energy savings, in the range of 5% to 10% while having minimal or even slightly positive impact on tokenization efficiency for the original training corpus.

Community

Submitted to ACL 2025 Student Research Workshop

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2506.18674 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2506.18674 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2506.18674 in a Space README.md to link it from this page.

Collections including this paper 1