Layout-Aware Parsing Meets Efficient LLMs: A Unified, Scalable Framework for Resume Information Extraction and Evaluation
This solves resume processing for talent acquisition, though it appears incremental as it combines existing techniques like layout parsing and LLM optimization.
The paper tackles automated resume information extraction by addressing layout heterogeneity, LLM cost/latency, and lack of standardized evaluation, presenting a framework that combines layout parsing, efficient LLM extraction, and automated evaluation. It shows a fine-tuned 0.6B LLM achieves top-tier accuracy while reducing latency and cost, with deployment in Alibaba's HR platform.
Automated resume information extraction is critical for scaling talent acquisition, yet its real-world deployment faces three major challenges: the extreme heterogeneity of resume layouts and content, the high cost and latency of large language models (LLMs), and the lack of standardized datasets and evaluation tools. In this work, we present a layout-aware and efficiency-optimized framework for automated extraction and evaluation that addresses all three challenges. Our system combines a fine-tuned layout parser to normalize diverse document formats, an inference-efficient LLM extractor based on parallel prompting and instruction tuning, and a robust two-stage automated evaluation framework supported by new benchmark datasets. Extensive experiments show that our framework significantly outperforms strong baselines in both accuracy and efficiency. In particular, we demonstrate that a fine-tuned compact 0.6B LLM achieves top-tier accuracy while significantly reducing inference latency and computational cost. The system is fully deployed in Alibaba's intelligent HR platform, supporting real-time applications across its business units.