Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning

TL;DR

The paper introduces ARTER, a structured pipeline that enhances entity linking by combining adaptive routing and targeted reasoning, achieving high accuracy with reduced reliance on expensive LLM-based inference.

Contribution

ARTER is a novel approach that selectively applies LLM reasoning to hard cases, improving efficiency and performance without extensive fine-tuning.

Findings

Outperforms ReFinED by up to +4.47% on benchmarks.

Achieves comparable accuracy to full LLM pipelines with half the LLM token usage.

Effectively categorizes cases to optimize reasoning resource allocation.

Abstract

Entity Linking (EL) has traditionally relied on large annotated datasets and extensive model fine-tuning. While recent few-shot methods leverage large language models (LLMs) through prompting to reduce training requirements, they often suffer from inefficiencies due to expensive LLM-based reasoning. ARTER (Adaptive Routing and Targeted Entity Reasoning) presents a structured pipeline that achieves high performance without deep fine-tuning by strategically combining candidate generation, context-based scoring, adaptive routing, and selective reasoning. ARTER computes a small set of complementary signals(both embedding and LLM-based) over the retrieved candidates to categorize contextual mentions into easy and hard cases. The cases are then handled by a low-computational entity linker (e.g. ReFinED) and more expensive targeted LLM-based reasoning respectively. On standard benchmarks, ARTER outperforms ReFinED by up to +4.47%, with an average gain of +2.53% on 5 out of 6 datasets, and performs comparably to pipelines using LLM-based reasoning for all mentions, while being as twice as efficient in terms of the number of LLM tokens.