Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval

TL;DR

This paper presents a large-scale, multidimensional analysis of over 100,000 recent research papers across AI fields, using advanced text processing to reveal evolving research trends and thematic shifts.

Contribution

It introduces a novel profiling pipeline combining topic clustering, LLM-assisted parsing, and structured retrieval to analyze research content at scale.

Findings

Growth in safety, multimodal reasoning, and agent-oriented research areas.

Stabilization of neural machine translation and graph-based methods.

Provides an evidence-based view of AI research evolution.

Abstract

The rapid expansion of research across machine learning, vision, and language has produced a volume of publications that is increasingly difficult to synthesize. Traditional bibliometric tools rely mainly on metadata and offer limited visibility into the semantic content of papers, making it hard to track how research themes evolve over time or how different areas influence one another.To obtain a clearer picture of recent developments, we compile a unified corpus of more than 100,000 papers from 22 major conferences between 2020 and 2025 and construct a multidimensional profiling pipeline to organize and analyze their textual content. By combining topic clustering, LLM-assisted parsing, and structured retrieval, we derive a comprehensive representation of research activity that supports the study of topic lifecycles, methodological transitions, dataset and model usage patterns, and institutional research directions.Our analysis highlights several notable shifts, including the growth of safety, multimodal reasoning, and agent-oriented studies, as well as the gradual stabilization of areas such as neural machine translation and graph-based methods. These findings provide an evidence-based view of how AI research is evolving and offer a resource for understanding broader trends and identifying emerging directions.