Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs

Sheridan Feucht, David Atkinson, Byron C Wallace, David Bau


Abstract
LLMs process text as sequences of tokens that roughly correspond to words, where less common words are represented by multiple tokens. However, individual tokens are often semantically unrelated to the meanings of the words/concepts they comprise. For example, Llama-2-7b’s tokenizer splits the word “patrolling” into two tokens, “pat” and “rolling”, neither of which correspond to semantically meaningful units like “patrol” or "-ing.” Similarly, the overall meanings of named entities like “Neil Young” and multi-word expressions like “break a leg” cannot be directly inferred from their constituent tokens. Mechanistically, how do LLMs convert such arbitrary groups of tokens into useful higher-level representations? In this work, we find that last token representations of named entities and multi-token words exhibit a pronounced “erasure” effect, where information about previous and current tokens is rapidly forgotten in early layers. Using this observation, we propose a method to “read out” the implicit vocabulary of an autoregressive LLM by examining differences in token representations across layers, and present results of this method for Llama-2-7b and Llama-3-8B. To our knowledge, this is the first attempt to probe the implicit vocabulary of an LLM.
Anthology ID:
2024.emnlp-main.543
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9727–9739
Language:
URL:
https://aclanthology.org/2024.emnlp-main.543
DOI:
10.18653/v1/2024.emnlp-main.543
Bibkey:
Cite (ACL):
Sheridan Feucht, David Atkinson, Byron C Wallace, and David Bau. 2024. Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9727–9739, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs (Feucht et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.543.pdf