interpretable embeddings

❓提問的嵌入empedings❓

通過詢問LLMS問題，QA-EMB論文的代碼來製作可解釋的嵌入。

Qa-Embs通過向預培訓的自回歸LLM提出一系列不是問題來構建可解釋的嵌入。

Quickstart

如果您只想在自己的應用程序中使用QA-EMB，則最簡單的方法是通過Imodelsx軟件包。要安裝，只需運行pip install imodelsx即可。

然後，您可以通過提出有關域的問題來生成自己的可解釋的嵌入：

 from imodelsx import QAEmb
import pandas as pd

questions = [
    'Is the input related to food preparation?' ,
    'Does the input mention laughter?' ,
    'Is there an expression of surprise?' ,
    'Is there a depiction of a routine or habit?' ,
    'Does the sentence contain stuttering?' ,
    'Does the input contain a first-person pronoun?' ,
]
examples = [
    'i sliced some cucumbers and then moved on to what was next' ,
    'the kids were giggling about the silly things they did' ,
    'and i was like whoa that was unexpected' ,
    'walked down the path like i always did' ,
    'um no um then it was all clear' ,
    'i was walking to school and then i saw a cat' ,
]

checkpoint = 'meta-llama/Meta-Llama-3-8B-Instruct'

embedder = QAEmb (
    questions = questions , checkpoint = checkpoint , use_cache = False )
embeddings = embedder ( examples )

df = pd . DataFrame ( embeddings . astype ( int ), columns = [
    q . split ()[ - 1 ] for q in questions ])
df . index = examples
df . columns . name = 'Question (abbreviated)'
display ( df . style . background_gradient ( axis = None ))
- - - - - - - - DISPLAYS ANSWER FOR EACH QUESTION IN EMBEDDING - - - - - - - -

數據集設置

在論文中重現fMRI實驗所需的數據集的說明。

• 使用python experiments/00_load_dataset.py
  • 在您運行的任何地方創建一個data元
• 將neuro1.config.root_dir設置為要存儲數據的位置
• 要{root_dir}/ds003020/derivative/pycortex-db/ flatmap
• 要運行ENG1000，需要從此處獲取em_data目錄，然後將其內容移至{root_dir}/em_data
• 加載響應
  • neuro1.data.response_utils功能load_response
  • 加載來自{root_dir}/ds003020/derivative/preprocessed_data/{subject} wheretheressmoke.h5響應，它們存儲在每個故事的H5文件中
• 加載刺激
  • neuro1.features.stim_utils功能load_story_wordseqs
  • 從{root_dir}/ds003020/derivative/TextGrids", where each story has a TextGrid file, eg wheretheressmoke.textgrid`
  • 使用{root_dir}/ds003020/derivative/respdict.json獲取每個故事的長度

代碼安裝

在此處安裝代碼作為完整開發的包裝的說明。

• 從repo目錄開始，從pip install -e .在本地安裝neuro1軟件包
• python 01_fit_encoding.py --subject UTS03 --feature eng1000
  • 編碼的其他可選參數。 py採用會話，ndelays，single_alpha，允許用戶更改所使用的線性回歸的數據量和正則化方面。
  • 然後，此功能將將模型性能指標和模型權重作為Numpy陣列保存。

引用

 @ misc { benara2024crafting ,
      title = { Crafting Interpretable Embeddings by Asking LLMs Questions }, 
      author = { Vinamra Benara and Chandan Singh and John X. Morris and Richard Antonello and Ion Stoica and Alexander G. Huth and Jianfeng Gao },
      year = { 2024 },
      eprint = { 2405.16714 },
      archivePrefix = { arXiv },
      primaryClass = { cs.CL }
}