paper-with-me

홈 › Papers

Identifying and Analyzing Task-Encoding Tokens in Large Language Models

2024-01-20 · Yu Bai, Heyan Huang, Cesare Spinoso-Di Piano, Marc-Antoine Rondeau, Sanxing Chen, Yang Gao, Jackie Chi Kit Cheung

In-context learning (ICL) has become an effective solution for few-shot learning in natural language processing. However, our understanding of ICL's working mechanisms is limited, specifically regarding how models learn to perform tasks from ICL demonstrations. For example, unexpectedly large changes in performance can arise from small changes in the prompt, leaving prompt design a largely empirical endeavour. In this paper, we investigate this problem by identifying and analyzing task-encoding tokens on whose representations the task performance depends. Using experiments that ablate the representations of different token types, we find that template and stopword tokens are the most prone to be task-encoding. In addition, we demonstrate experimentally that lexical meaning, repetition, and text formatting are the main distinguishing characteristics of these tokens. Our work sheds light on how large language models (LLMs) learn to perform a task from demonstrations, deepens our understanding of the varied roles different types of tokens play in LLMs, and provides insights for avoiding instability from improperly utilizing task-encoding tokens.

📄 PDF Abstract BibTeX arXiv:2401.11323

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyFew-Shot LearningIn-Context Learning

Similar Papers 제목 키워드 기반

Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models

2024-05-28 · Sangmin Woo, Donguk Kim, Jaehyuk Jang, Yubin Choi 외

This study addresses the issue observed in Large Vision Language Models (LVLMs), where excessive attention on a few image tokens, referred to as blind tokens, leads to hallucinatory responses in tasks requiring fine-grai…

MMEObject

Baselines for Identifying Watermarked Large Language Models

2023-05-29 · Leonard Tang, Gavin Uberti, Tom Shlomi

We consider the emerging problem of identifying the presence and use of watermarking schemes in widely used, publicly hosted, closed source large language models (LLMs). We introduce a suite of baseline algorithms for id…

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models

2025-10-10 · Hoigi Seo, Dong Un Kang, Hyunjin Cho, Joohoon Lee 외 arxiv

Large vision-language models (LVLMs), which integrate a vision encoder (VE) with a large language model, have achieved remarkable success across various tasks. However, there are still crucial challenges in LVLMs such as…

Struct-X: Enhancing Large Language Models Reasoning with Structured Data

2024-07-17 · Xiaoyu Tan, Haoyu Wang, Xihe Qiu, Yuan Cheng 외

Structured data, rich in logical and relational information, has the potential to enhance the reasoning abilities of large language models (LLMs). Still, its integration poses a challenge due to the risk of overwhelming …

Data AugmentationReading Comprehension

LBPE: Long-token-first Tokenization to Improve Large Language Models

2024-11-08 · Haoran Lian, Yizhe Xiong, Zijia Lin, Jianwei Niu 외

The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its success, a critical challenge persists:…

Language ModelingLanguage Modelling