Summary of Mind: Effective Incorrect Assignment Detection Through a Multi-modal Structure-enhanced Language Model, by Yunhe Pang et al.
MIND: Effective Incorrect Assignment Detection through a Multi-Modal Structure-Enhanced Language Model
by Yunhe Pang, Bo Chen, Fanjin Zhang, Yanghui Rao, Jie Tang
First submitted to arxiv on: 5 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed paper addresses the issue of author name ambiguity in online digital libraries by introducing a structure-enhanced language model. The model combines graph-based and semantic-based features from papers to detect incorrect assignments. It is trained using a multi-modal multi-turn instruction tuning framework, which incorporates task-guided instruction tuning, text-attribute modality, and structural modality. Experimental results show that the proposed model outperforms previous approaches, achieving top performance on the KDD Cup 2024 leaderboard. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper solves a big problem in how we store and organize academic papers online. When someone searches for a specific author’s work, they might get incorrect results because of mistakes in who wrote what. The current methods to fix this are not good enough. So, the researchers created a new way to detect these errors using language models that look at both the text inside papers and how those texts relate to each other. This new method is very effective and beats all previous approaches. |
Keywords
» Artificial intelligence » Instruction tuning » Language model » Multi modal
