Related Experiment Video
Updated: Sep 9, 2025
03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
681
Scalable Scientific Interest Profiling Using Large Language Models
Yilun Liang1,2, Gongbo Zhang1, Edward Sun3
1Department of Biomedical Informatics, Columbia University, New York, NY, USA.
Arxiv
|September 2, 2025
Summary
Large Language Models (LLMs) can automate scientific interest profiling. Profiles generated using Medical Subject Headings (MeSH) terms showed better readability and were preferred over abstract-based profiles, despite differences from human-written summaries.
Area of Science:
- Biomedical Informatics
- Artificial Intelligence in Research
- Scientific Communication
Background:
- Scientist research profiles are crucial for talent discovery and collaboration but are often outdated.
- Automated and scalable methods are needed to maintain current research profiles.
Purpose of the Study:
- To design and evaluate Large Language Models (LLMs)-based methods for generating scientific interest profiles.
- To compare machine-generated profiles (from PubMed abstracts and MeSH terms) with researchers' self-summarized interests.
Main Methods:
- Utilized GPT-4o-mini to summarize research interests for 595 faculty members based on their PubMed abstracts and MeSH terms.
- Collected publication data (titles, MeSH terms, abstracts) from CUIMC faculty.
- Conducted manual and automated evaluations to compare machine-generated and self-written profiles.
Main Results:
- Lexical overlap was low between machine-generated and self-written profiles (low ROUGE-L, BLEU, METEOR scores).
- Moderate semantic similarity was found using BERTScore (F1: 0.542 MeSH-based, 0.555 abstract-based).
- Manual reviews favored MeSH-based profiles (67.86%) for readability (93.44%) and overall impression (77.78% good/excellent).
Conclusions:
- LLMs offer a scalable solution for automating scientific interest profiling.
- MeSH-term-derived profiles demonstrate superior readability and user preference compared to abstract-derived profiles.
- Machine-generated profiles differ in concept choice from human-written ones, highlighting potential for novel idea generation in manual profiles.
Keywords:
Kullback-Leibler DivergenceLarge Language ModelsNatural Language GenerationResearcher ProfilingMore Related Videos
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
570
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
7.7K
Related Concept Videos
02:07Improving Translational Accuracy
11.8K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.8K
02:24Ribosome Profiling
3.6K
Ribosome profiling or ribo-sequencing is a deep sequencing technique that produces a snapshot of active translation in a cell. It selectively sequences the mRNAs protected by ribosomes to get an insight into a cell’s translation landscape at any given point in time.
Applications of ribosome profiling
Ribosome profiling has many applications, including in vivo monitoring of translation inside a particular organ or tissue type and quantifying new protein synthesis levels.
The technique...
Applications of ribosome profiling
Ribosome profiling has many applications, including in vivo monitoring of translation inside a particular organ or tissue type and quantifying new protein synthesis levels.
The technique...
3.6K
01:22Language Development
444
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
444
01:26Scaling
314
In designing and analyzing filters, resonant circuits, or circuit analysis at large, working with standard element values like 1 ohm, 1 henry, or 1 farad can be convenient before scaling these values to more realistic figures. This approach is widely utilized by not employing realistic element values in numerous examples and problems; it simplifies mastering circuit analysis through convenient component values. The complexity of calculations is thereby reduced, with the understanding that...
314
01:27Language and Cognition
438
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
438
01:29Aggregates Classification
380
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
380