Identifying and Analyzing Performance-Critical Tokens in Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908651478843392 |
|---|---|
| author | Bai, Yu Huang, Heyan Piano, Cesare Spinoso-Di Rondeau, Marc-Antoine Chen, Sanxing Gao, Yang Cheung, Jackie Chi Kit |
| author_facet | Bai, Yu Huang, Heyan Piano, Cesare Spinoso-Di Rondeau, Marc-Antoine Chen, Sanxing Gao, Yang Cheung, Jackie Chi Kit |
| contents | In-context learning (ICL) has emerged as an effective solution for few-shot learning with large language models (LLMs). However, how LLMs leverage demonstrations to specify a task and learn a corresponding computational function through ICL is underexplored. Drawing from the way humans learn from content-label mappings in demonstrations, we categorize the tokens in an ICL prompt into content, stopword, and template tokens. Our goal is to identify the types of tokens whose representations directly influence LLM's performance, a property we refer to as being performance-critical. By ablating representations from the attention of the test example, we find that the representations of informative content tokens have less influence on performance compared to template and stopword tokens, which contrasts with the human attention to informative words. We give evidence that the representations of performance-critical tokens aggregate information from the content tokens. Moreover, we demonstrate experimentally that lexical meaning, repetition, and structural cues are the main distinguishing characteristics of these tokens. Our work sheds light on how large language models learn to perform tasks from demonstrations and deepens our understanding of the roles different types of tokens play in large language models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_11323 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Identifying and Analyzing Performance-Critical Tokens in Large Language Models Bai, Yu Huang, Heyan Piano, Cesare Spinoso-Di Rondeau, Marc-Antoine Chen, Sanxing Gao, Yang Cheung, Jackie Chi Kit Computation and Language In-context learning (ICL) has emerged as an effective solution for few-shot learning with large language models (LLMs). However, how LLMs leverage demonstrations to specify a task and learn a corresponding computational function through ICL is underexplored. Drawing from the way humans learn from content-label mappings in demonstrations, we categorize the tokens in an ICL prompt into content, stopword, and template tokens. Our goal is to identify the types of tokens whose representations directly influence LLM's performance, a property we refer to as being performance-critical. By ablating representations from the attention of the test example, we find that the representations of informative content tokens have less influence on performance compared to template and stopword tokens, which contrasts with the human attention to informative words. We give evidence that the representations of performance-critical tokens aggregate information from the content tokens. Moreover, we demonstrate experimentally that lexical meaning, repetition, and structural cues are the main distinguishing characteristics of these tokens. Our work sheds light on how large language models learn to perform tasks from demonstrations and deepens our understanding of the roles different types of tokens play in large language models. |
| title | Identifying and Analyzing Performance-Critical Tokens in Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.11323 |