Elliot Meyerson
Research Subjects
Research Interests
Elliot Meyerson has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Adam Gaier
Autodesk Research, 53111 Bonn, Germany
1 shared publication - Aditya Rawal
Mark Wainwright Analytical Centre University of New South Wales (UNSW) Sydney New South Wales 2052 Australia
1 shared publication - Amy K. Hoover
New Jersey Institute of Technology, Newark, NJ, USA
1 shared publication Angela Serra
1 shared publication- Arash Moradi Karkaj
New Jersey Institute of Technology, Newark, NJ, USA
1 shared publication Arshak Navruzyan
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 28 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Evolutionary Learning and Optimization
- Vol. 4 (4) , 1-40
Language Model Crossover: Variation through Few-Shot Prompting
This article pursues the insight that language models naturally enable an intelligent variation operator similar in spirit to evolutionary crossover. In particular, language models of sufficient scale demonstrate in-context learning, i.e., they can learn from associations between a small number of input patterns to generate outputs incorporating such associations (also called few-shot prompting). This ability can be leveraged to form a simple but powerful variation operator, i.e., to prompt a language model with a few text-based genotypes (such as code, plain-text sentences, or equations), and to parse its corresponding output as those genotypes’ offspring. The promise of such language model crossover (which is simple to implement and can leverage many different open source language models) is that it enables a simple mechanism to evolve semantically rich text representations (with few domain-specific tweaks), and naturally benefits from current progress in language models. Experiments in this article highlight the versatility of language-model crossover, through evolving binary bit-strings, sentences, equations, text-to-image prompts, and Python code. The conclusion is that language model crossover is a flexible and effective method for evolving genomes representable as text.
- 28 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Evolutionary Learning and Optimization
- Vol. 4 (4) , 1-40
Top Cited PapersOpen AccessLanguage Model Crossover: Variation through Few-Shot Prompting
This article pursues the insight that language models naturally enable an intelligent variation operator similar in spirit to evolutionary crossover. In particular, language models of sufficient scale demonstrate in-context learning, i.e., they can learn from associations between a small number of input patterns to generate outputs incorporating such associations (also called few-shot prompting). This ability can be leveraged to form a simple but powerful variation operator, i.e., to prompt a language model with a few text-based genotypes (such as code, plain-text sentences, or equations), and to parse its corresponding output as those genotypes’ offspring. The promise of such language model crossover (which is simple to implement and can leverage many different open source language models) is that it enables a simple mechanism to evolve semantically rich text representations (with few domain-specific tweaks), and naturally benefits from current progress in language models. Experiments in this article highlight the versatility of language-model crossover, through evolving binary bit-strings, sentences, equations, text-to-image prompts, and Python code. The conclusion is that language model crossover is a flexible and effective method for evolving genomes representable as text.
- 20 October 2023
- Published by Elsevier
Contributors