DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing

Guardado en:
Detalles Bibliográficos
Publicado en:arXiv.org (Dec 8, 2024), p. n/a
Autor principal: Shankar, Shreya
Otros Autores: Chambers, Tristan, Shah, Tarak, Parameswaran, Aditya G, Wu, Eugene
Publicado:
Cornell University Library, arXiv.org
Materias:
Acceso en línea:Citation/Abstract
Full text outside of ProQuest
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3142726310
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3142726310 
045 0 |b d20241208 
100 1 |a Shankar, Shreya 
245 1 |a DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing 
260 |b Cornell University Library, arXiv.org  |c Dec 8, 2024 
513 |a Working Paper 
520 3 |a Analyzing unstructured data has been a persistent challenge in data processing. Large Language Models (LLMs) have shown promise in this regard, leading to recent proposals for declarative frameworks for LLM-powered processing of unstructured data. However, these frameworks focus on reducing cost when executing user-specified operations using LLMs, rather than improving accuracy, executing most operations as-is (in a single LLM call). This is problematic for complex tasks and data, where LLM outputs for user-defined operations are often inaccurate, even with optimized prompts. For example, an LLM may struggle to identify {\em all} instances of specific clauses, like force majeure or indemnification, in lengthy legal documents, requiring decomposition of the data, the task, or both. We present DocETL, a system that optimizes complex document processing pipelines, while accounting for LLM shortcomings. DocETL offers a declarative interface for users to define such pipelines and uses an agent-based approach to automatically optimize them, leveraging novel agent-based rewrites (that we call rewrite directives), as well as an optimization and evaluation framework. We introduce (i) logical rewriting of pipelines, tailored for LLM-based tasks, (ii) an agent-guided plan evaluation mechanism that synthesizes and orchestrates task-specific validation prompts, and (iii) an optimization algorithm that efficiently finds promising plans, considering the latencies of agent-based plan generation and evaluation. Our evaluation on four different unstructured document analysis tasks demonstrates that DocETL finds plans with outputs that are 25 to 80% more accurate than well-engineered baselines, addressing a critical gap in unstructured data analysis. DocETL is open-source at docetl.org, and as of November 2024, has amassed over 1.3k GitHub Stars, with users spanning a variety of domains. 
653 |a Data analysis 
653 |a Algorithms 
653 |a Data processing 
653 |a Prompt engineering 
653 |a Unstructured data 
653 |a Large language models 
653 |a Task complexity 
653 |a Documents 
653 |a Query languages 
653 |a Optimization 
700 1 |a Chambers, Tristan 
700 1 |a Shah, Tarak 
700 1 |a Parameswaran, Aditya G 
700 1 |a Wu, Eugene 
773 0 |t arXiv.org  |g (Dec 8, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3142726310/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2410.12189