Difference between revisions of "Contextual Literature-Based Discovery (C-LBD)"
m |
m |
||
| Line 23: | Line 23: | ||
</i></b></center><hr> | </i></b></center><hr> | ||
| + | |||
| + | Contextual Literature-Based Discovery (C-LBD) developed by researchers at the University of Illinois at Urbana-Champaign, the Hebrew University of Jerusalem, and the Allen Institute for Artificial Intelligence (AI2). C-LBD aims to address the limitations of traditional literature-based discovery (LBD) by using a natural language setting to constrain the generation space for LBD and generate sentences. The researchers introduce a novel modeling framework for C-LBD that can gather inspiration from disparate sources and use them to form novel hypotheses. They also introduce an in-context contrastive model to promote creative thinking. The team believes that expanding C-LBD to include a multimodal analysis of formulas, tables, and figures to provide a more comprehensive and enriched background context is an intriguing direction to investigate in the future. The use of advanced LLMs like GPT-4, which is currently in development, is another avenue to investigate. [https://www.marktechpost.com/2023/05/29/can-language-models-generate-new-scientific-ideas-meet-contextualized-literature-based-discovery-c-lbd/ Can Language Models Generate New Scientific Ideas? Meet Contextualized Literature-Based Discovery (C-LBD) | Tanushree Shenwai - MarkTechPost] | ||
<img src="https://i.redd.it/doao39n1es2b1.png" width="800"> | <img src="https://i.redd.it/doao39n1es2b1.png" width="800"> | ||
| − | |||
| − | |||
| − | |||
The assistant accepts as input (1) relevant information, such as present challenges, motives, and constraints, and (2) a seed phrase that should be the primary focus of the developed scientific concept. Given this information, the team investigates two forms of C-LBD: | The assistant accepts as input (1) relevant information, such as present challenges, motives, and constraints, and (2) a seed phrase that should be the primary focus of the developed scientific concept. Given this information, the team investigates two forms of C-LBD: | ||
* one that generates a full phrase explaining an idea | * one that generates a full phrase explaining an idea | ||
* and another that generates only a salient component of the idea. | * and another that generates only a salient component of the idea. | ||
Revision as of 20:11, 30 May 2023
YouTube ... Quora ...Google search ...Google News ...Bing News
- In-Context Learning (ICL) ... Context ... Causation vs. Correlation ... Autocorrelation ... Out-of-Distribution (OOD) Generalization ... Transfer Learning
- Assistants ... Agents ... Negotiation ... LangChain
- Learning to Generate Novel Scientific Directions with Contextualized Literature-based Discovery | Q. Wang, D. Downey, H. Ji, & T. Hope - arXiv - Cornell University
- C-LBD | GitHub
Inspired from the idea that an AI assistant that can provide suggestions in plain English, including unique thoughts and connections.
Contextual Literature-Based Discovery (C-LBD) developed by researchers at the University of Illinois at Urbana-Champaign, the Hebrew University of Jerusalem, and the Allen Institute for Artificial Intelligence (AI2). C-LBD aims to address the limitations of traditional literature-based discovery (LBD) by using a natural language setting to constrain the generation space for LBD and generate sentences. The researchers introduce a novel modeling framework for C-LBD that can gather inspiration from disparate sources and use them to form novel hypotheses. They also introduce an in-context contrastive model to promote creative thinking. The team believes that expanding C-LBD to include a multimodal analysis of formulas, tables, and figures to provide a more comprehensive and enriched background context is an intriguing direction to investigate in the future. The use of advanced LLMs like GPT-4, which is currently in development, is another avenue to investigate. Can Language Models Generate New Scientific Ideas? Meet Contextualized Literature-Based Discovery (C-LBD) | Tanushree Shenwai - MarkTechPost
The assistant accepts as input (1) relevant information, such as present challenges, motives, and constraints, and (2) a seed phrase that should be the primary focus of the developed scientific concept. Given this information, the team investigates two forms of C-LBD:
- one that generates a full phrase explaining an idea
- and another that generates only a salient component of the idea.
