chensyCN/llm4ea_official
[NeurIPS‘24] LLM4EA: Entity Alignment with Noisy Annotations from Large Language Models
This project helps data professionals tasked with combining information about the same real-world entities (like people, places, or products) from different databases. It takes diverse entity data as input and produces a consolidated, more accurate set of aligned entities, even when initial information is incomplete or inconsistent. This tool is for data scientists, knowledge graph engineers, or anyone building robust data integrations and needing to deduplicate or link entities across disparate sources.
No commits in the last 6 months.
Use this if you need to accurately identify and merge identical entities across multiple datasets, especially when dealing with ambiguous or noisy entity descriptions that make direct matching difficult.
Not ideal if your entity alignment needs are simple string matching or if you lack access to or willingness to use large language models for annotation.
Stars
61
Forks
6
Language
Python
License
GPL-3.0
Category
Last pushed
Oct 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/chensyCN/llm4ea_official"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
steering-vectors/steering-vectors
Steering vectors for transformer language models in Pytorch / Huggingface
jianghoucheng/AlphaEdit
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)
kmeng01/memit
Mass-editing thousands of facts into a transformer memory (ICLR 2023)
boyiwei/alignment-attribution-code
[ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
jianghoucheng/AnyEdit
AnyEdit: Edit Any Knowledge Encoded in Language Models, ICML 2025