The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models

arXiv:2609.31341 · cs.AI, cs.CL · Submitted 2026-09-25 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/chrewbroccoli/local-ie-energy

Terminology

• Accuracy — 33× in this paper · explained in 1 episode
• Quantization — 27× in this paper · explained in 12 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Benchmarking — 9× in this paper · explained in 3 episodes
• Energy Efficiency — 4× in this paper · explained in 3 episodes
• Average Field Exact Match — 3× in this paper
• Adaptation — 2× in this paper · explained in 1 episode
• Fidelity — 2× in this paper · explained in 2 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Fuzzy Match Score — 1× in this paper
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures
• WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs
• AgenticIE: An Adaptive Agent for Information Extraction from Complex Regulatory Documents
• DeepSeek-OCR 2: Visual Causal Flow
• Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use
• BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding
• Deep Learning based Visually Rich Document Content Understanding: A Survey
• The Llama 3 Herd of Models
• Mistral 7B
• Chargrid: Towards Understanding 2D Documents
• Cooling Matters: Benchmarking Large Language Models and Vision-Language Models on Liquid-Cooled Versus Air-Cooled H100 GPU Systems
• AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
• Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion
• LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
• Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models
• Benchmarking Energy Efficiency of Large Language Models Using vLLM
• Qwen3 Technical Report
• Bench360: Benchmarking Local LLM Inference from 360 Degrees
• Large Language Models for Generative Information Extraction: A Survey

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection