A Survey on Hypothesis Generation for Scientific Discovery in the Era of Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alkan, Atilla Kaan, Sourav, Shashwat, Jablonska, Maja, Astarita, Simone, Chakrabarty, Rishabh, Garuda, Nikhil, Khetarpal, Pranav, Pióro, Maciej, Tanoglidis, Dimitrios, Iyer, Kartheik G., Polimera, Mugdha S., Smith, Michael J., Ghosal, Tirthankar, Huertas-Company, Marc, Kruk, Sandor, Schawinski, Kevin, Ciucă, Ioana
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917979706359808
author Alkan, Atilla Kaan
Sourav, Shashwat
Jablonska, Maja
Astarita, Simone
Chakrabarty, Rishabh
Garuda, Nikhil
Khetarpal, Pranav
Pióro, Maciej
Tanoglidis, Dimitrios
Iyer, Kartheik G.
Polimera, Mugdha S.
Smith, Michael J.
Ghosal, Tirthankar
Huertas-Company, Marc
Kruk, Sandor
Schawinski, Kevin
Ciucă, Ioana
author_facet Alkan, Atilla Kaan
Sourav, Shashwat
Jablonska, Maja
Astarita, Simone
Chakrabarty, Rishabh
Garuda, Nikhil
Khetarpal, Pranav
Pióro, Maciej
Tanoglidis, Dimitrios
Iyer, Kartheik G.
Polimera, Mugdha S.
Smith, Michael J.
Ghosal, Tirthankar
Huertas-Company, Marc
Kruk, Sandor
Schawinski, Kevin
Ciucă, Ioana
contents Hypothesis generation is a fundamental step in scientific discovery, yet it is increasingly challenged by information overload and disciplinary fragmentation. Recent advances in Large Language Models (LLMs) have sparked growing interest in their potential to enhance and automate this process. This paper presents a comprehensive survey of hypothesis generation with LLMs by (i) reviewing existing methods, from simple prompting techniques to more complex frameworks, and proposing a taxonomy that categorizes these approaches; (ii) analyzing techniques for improving hypothesis quality, such as novelty boosting and structured reasoning; (iii) providing an overview of evaluation strategies; and (iv) discussing key challenges and future directions, including multimodal integration and human-AI collaboration. Our survey aims to serve as a reference for researchers exploring LLMs for hypothesis generation.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05496
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Survey on Hypothesis Generation for Scientific Discovery in the Era of Large Language Models
Alkan, Atilla Kaan
Sourav, Shashwat
Jablonska, Maja
Astarita, Simone
Chakrabarty, Rishabh
Garuda, Nikhil
Khetarpal, Pranav
Pióro, Maciej
Tanoglidis, Dimitrios
Iyer, Kartheik G.
Polimera, Mugdha S.
Smith, Michael J.
Ghosal, Tirthankar
Huertas-Company, Marc
Kruk, Sandor
Schawinski, Kevin
Ciucă, Ioana
Computation and Language
68T50
Hypothesis generation is a fundamental step in scientific discovery, yet it is increasingly challenged by information overload and disciplinary fragmentation. Recent advances in Large Language Models (LLMs) have sparked growing interest in their potential to enhance and automate this process. This paper presents a comprehensive survey of hypothesis generation with LLMs by (i) reviewing existing methods, from simple prompting techniques to more complex frameworks, and proposing a taxonomy that categorizes these approaches; (ii) analyzing techniques for improving hypothesis quality, such as novelty boosting and structured reasoning; (iii) providing an overview of evaluation strategies; and (iv) discussing key challenges and future directions, including multimodal integration and human-AI collaboration. Our survey aims to serve as a reference for researchers exploring LLMs for hypothesis generation.
title A Survey on Hypothesis Generation for Scientific Discovery in the Era of Large Language Models
topic Computation and Language
68T50
url https://arxiv.org/abs/2504.05496