HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vasu, Rosni, Basu, Chandrayee, Mishra, Bhavana Dalvi, Sarasua, Cristina, Clark, Peter, Bernstein, Abraham
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916911679275008
author Vasu, Rosni
Basu, Chandrayee
Mishra, Bhavana Dalvi
Sarasua, Cristina
Clark, Peter
Bernstein, Abraham
author_facet Vasu, Rosni
Basu, Chandrayee
Mishra, Bhavana Dalvi
Sarasua, Cristina
Clark, Peter
Bernstein, Abraham
contents Large Language models have demonstrated promising performance in research ideation across scientific domains. Hypothesis development, the process of generating a highly specific declarative statement connecting a research idea with empirical validation, has received relatively less attention. Existing approaches trivially deploy retrieval augmentation and focus only on the quality of the final output ignoring the underlying reasoning process behind ideation. We present $\texttt{HypER}$ ($\textbf{Hyp}$othesis Generation with $\textbf{E}$xplanation and $\textbf{R}$easoning), a small language model (SLM) trained for literature-guided reasoning and evidence-based hypothesis generation. $\texttt{HypER}$ is trained in a multi-task setting to discriminate between valid and invalid scientific reasoning chains in presence of controlled distractions. We find that $\texttt{HypER}$ outperformes the base model, distinguishing valid from invalid reasoning chains (+22\% average absolute F1), generates better evidence-grounded hypotheses (0.327 vs. 0.305 base model) with high feasibility and impact as judged by human experts ($>$3.5 on 5-point Likert scale).
format Preprint
id arxiv_https___arxiv_org_abs_2506_12937
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance
Vasu, Rosni
Basu, Chandrayee
Mishra, Bhavana Dalvi
Sarasua, Cristina
Clark, Peter
Bernstein, Abraham
Artificial Intelligence
Computation and Language
Large Language models have demonstrated promising performance in research ideation across scientific domains. Hypothesis development, the process of generating a highly specific declarative statement connecting a research idea with empirical validation, has received relatively less attention. Existing approaches trivially deploy retrieval augmentation and focus only on the quality of the final output ignoring the underlying reasoning process behind ideation. We present $\texttt{HypER}$ ($\textbf{Hyp}$othesis Generation with $\textbf{E}$xplanation and $\textbf{R}$easoning), a small language model (SLM) trained for literature-guided reasoning and evidence-based hypothesis generation. $\texttt{HypER}$ is trained in a multi-task setting to discriminate between valid and invalid scientific reasoning chains in presence of controlled distractions. We find that $\texttt{HypER}$ outperformes the base model, distinguishing valid from invalid reasoning chains (+22\% average absolute F1), generates better evidence-grounded hypotheses (0.327 vs. 0.305 base model) with high feasibility and impact as judged by human experts ($>$3.5 on 5-point Likert scale).
title HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2506.12937