大语言模型在表格任务中的应用 On the Use of Large Language Models for Table Tasks.docx

1

OntheUseofLargeLanguageModels

forTableTasks

-Introduction

HaochenZhangChuanXiaoYuyangDong

Tabulardataiseverywhere

(a)Relationaldatabases

(b)Richdocuments,PDF

(c)webpages(d)spreadsheet2

Growingresearchfocus

?GrowquicklyinDB,AIandNLPcommunities

resultfrom[4]

?Recenttutorials

?[1]Webtableextraction,retrievalandaugmentation,SIGIR19

?[2]FromTablestoKnowledge:RecentAdvancesinTableUnderstanding,KDD21

?[3]TransformersforTabularDataRepresentation:AtutorialonModelsandApplicationsVLDB22,SIGMOD23

?[4]LargeLanguageModelsforTabularData:ProgressesandFutureDirections,SIGIR24

?A-Paper-List-of-Awesome-Tabular-LLMs，/SpursGoZmy/Awesome-Tabular-LLMs

Tabletasksbenchmarks

?

?TableInterpretation

?EntityLinking

?ColumnTypeAnnotation

?RelationExtraction

?Tabledetection

Tablereprocessing

?Tablematching

?Entitymatching

?Schemamatching

?Tablecleaning

?Errordetection

?Dataimputation

?Tableaugmentation

?Rowpopulation

?Schemaaugmentation

?Tablesearch

?Tabletransformation

Tableunderstanding“Understandtables”

Tableunderstanding

Tableanalysis

?TableQA

?Tablefactverification

?Table-to-text

?Text-to-SQL

4

5

Table

preprocessing

“Matchingtworows”

Schema

Schemamatching

Table

Tablematching

matching

matching

Entity

Entity

AAABBBCCC

AAA

BBB

CCC

EEE

AAA’

idnamerev1IBMCorp$57B

id

name

rev

1

IBMCorp

$57B

2

AppleInc

$366B

3

GE

$74B

DDD

id

name

loc

#of

employee

1

Apple

CA

154,000

2

IBM

NY

282,000

?Datasetandbenchmark

1.CanFoundationModelsWrangleYourData?[VLDB23]./abs/2205.09911

2.Jellyfish:Instruction-TuningLocalLargeLanguageModelsforDataPreprocessing[EMNLP24]/abs/2312.01678

IDName

ID

Name

DateofBirth

Prefecture

PostalCode

Height

1

Y