Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Inductive-bias Learning: 大規模言語モデルによる予測モデルの生成

Toma Tanaka
March 16, 2024

Inductive-bias Learning: 大規模言語モデルによる予測モデルの生成

NLP2024で発表した資料です.LLMを使い機械学習モデルに匹敵する予測を行うことができるモデルをプログラミングのコードとして生成する研究です.

Toma Tanaka

March 16, 2024
Tweet

More Decks by Toma Tanaka

Other Decks in Science

Transcript

  1. Inductive-bias Learning: The views expressed here are our own and

    do not necessarily reflect the views of Brainpad Inc. Any errors and inadequacies are our own. B7-5 30 (NLP2024) B7: 2024/3/13( ) 11:15-13:05
  2. 3

  3. 4

  4. In-context Learning In-context Learning(ICL) LLM [Brown20] (※ ) 5 [Brown20]”Language

    Models are Few-Shot Learners”, NeurIPS 2020 ※LLM Large Language Model Input Output 5 + 8 = 13 7 + 2 =   9 1 + 0 =  1 3 + 4 =  7 5 + 9 = 14 9 + 8 =   LLM 17 Prompt Prediction
  5. In-context Learning LLM In-context Learning “ ” “ ” “

    ” LLM 本研究では、“LLMがデータからどの程度論理関係を把握し、 その知識やルールを出力できるか”を明らかにすることを目指す In-context Learning 6
  6. 7 ICL [Chan22] ICL ICL [von Oswald23] Transformer ICL meta

    learning ICL [Garg22] 2 [Chan22]”Data Distributional Properties Drive Emergent In-Context Learning in Transformers”, NeurIPS 2022 [von Oswald23]”Transformers learn in-context by gradient descent.” ICML 2023 [Garg22]”What Can Transformers Learn In-Context? A Case Study of Simple Function Classes”, NeurIPS 2022
  7. 9

  8. Inductive-bias Learning Inductive-bias Learning(IBL) IBL LLM 10 IBLのための指示 x1 x2 y 1 3 0

    2 4 1 7 1 0 5 2 0 8 7 1 4 9 1 LLM def model(x1, x2):   if x1 > 4:     y = 1   else:     y = 0   return y Prompt Prediction ※Inductive-bias Learning(IBL) ICL IBL ( )
  9. In-context Learning 12 IBL Python IBLのための指示 x1 x2 y 1 3 0 2 4 1 7 1 0

    5 2 0 8 7 1 4 9 1 def model(x1, x2):   if x1 > 4:     y = 1   else:     y = 0   return y LLM Prompt Output( ) Inductive-bias Learning (IBL) Prompt LLM 1 Output( ) In-context Learning (ICL) x1 x2 y 1 3 0 2 4 1 7 1 0 5 2 0 8 7 1 4 9 
  10. 13

  11. LLM gpt-4-0613 2023 6 13 gpt-4 Logistic Regression K-NN SVM

    Linear Kernel LLM 14 gpt-4-0613 https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo Logistic Regression https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html K-NN https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html SVM Linear Kernel https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html
  12. Pseudo Dataset Moon Dataset 3 seed IBL IBL 30 ROC-AUC

    15 Psuedo Datasets https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_classification.html Moon Datasets https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_moons.html Moon Dataset
  13. 16

  14. 20

  15. “GPT-4 Turbo” “Gemini ”,“Claude 3” LLM IBL LLM IBL Fine

    Tuning Fine Tuning AI AI 23 IBL OSS GitHub https://github.com/fuyu-quant/IBLM GPT-4 Turbo https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo Gemini https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/gemini Claude3 https://www.anthropic.com/api
  16. IBL 16 IBLのための指示 学習データの挿入 x1 x2 y 1 3 0 2 4 1 7 1 0 ・・・ def

    model(x1, x2):   if x1 > 4:     y = 1   else:     y = 0   return y LLM 10件の学習データ 20件の学習データ 300件の学習データ テストデータ ROC-AUC 30 10,20,30,40,50,100,200,300 1000 LLM seed 30