HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction
October 10, 2024 Β· Declared Dead Β· π Neural Information Processing Systems
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Qianyue Hao, Jingyang Fan, Fengli Xu, Jian Yuan, Yong Li
arXiv ID
2410.09112
Category
cs.DL: Digital Libraries
Cross-listed
cs.AI,
cs.CL
Citations
16
Venue
Neural Information Processing Systems
Last Checked
6 months ago
Abstract
Citation networks are critical in modern science, and predicting which previous papers (candidates) will a new paper (query) cite is a critical problem. However, the roles of a paper's citations vary significantly, ranging from foundational knowledge basis to superficial contexts. Distinguishing these roles requires a deeper understanding of the logical relationships among papers, beyond simple edges in citation networks. The emergence of LLMs with textual reasoning capabilities offers new possibilities for discerning these relationships, but there are two major challenges. First, in practice, a new paper may select its citations from gigantic existing papers, where the texts exceed the context length of LLMs. Second, logical relationships between papers are implicit, and directly prompting an LLM to predict citations may result in surface-level textual similarities rather than the deeper logical reasoning. In this paper, we introduce the novel concept of core citation, which identifies the critical references that go beyond superficial mentions. Thereby, we elevate the citation prediction task from a simple binary classification to distinguishing core citations from both superficial citations and non-citations. To address this, we propose $\textbf{HLM-Cite}$, a $\textbf{H}$ybrid $\textbf{L}$anguage $\textbf{M}$odel workflow for citation prediction, which combines embedding and generative LMs. We design a curriculum finetune procedure to adapt a pretrained text embedding model to coarsely retrieve high-likelihood core citations from vast candidates and then design an LLM agentic workflow to rank the retrieved papers through one-shot reasoning, revealing the implicit relationships among papers. With the pipeline, we can scale the candidate sets to 100K papers. We evaluate HLM-Cite across 19 scientific fields, demonstrating a 17.6% performance improvement comparing SOTA methods.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Digital Libraries
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Measuring academic influence: Not all citations are equal
R.I.P.
π»
Ghosted
The Open Access Advantage Considering Citation, Article Usage and Social Media Attention
R.I.P.
π»
Ghosted
A Bibliometric Review of Large Language Models Research from 2017 to 2023
R.I.P.
π»
Ghosted
On the Performance of Hybrid Search Strategies for Systematic Literature Reviews in Software Engineering
R.I.P.
π»
Ghosted
A Systematic Identification and Analysis of Scientists on Twitter
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted