English
Related papers

Related papers: Sparks of Science: Hypothesis Generation Using Str…

200 papers

Large language models (LLMs) have shown potential in assisting scientific research, yet their ability to discover high-quality research hypotheses remains unexamined due to the lack of a dedicated benchmark. To address this gap, we…

Computation and Language · Computer Science 2026-04-21 Yujie Liu , Zonglin Yang , Tong Xie , Jinjie Ni , Ben Gao , Yuqiang Li , Shixiang Tang , Wanli Ouyang , Erik Cambria , Dongzhan Zhou

Knowledge hypergraphs surpass traditional binary knowledge graphs by encapsulating complex $n$-ary atomic facts, providing a more comprehensive paradigm for semantic representation. However, constructing high-quality hypergraphs remains…

Computation and Language · Computer Science 2026-02-24 Rizhuo Huang , Yifan Feng , Rundong Xue , Shihui Ying , Jun-Hai Yong , Chuan Shi , Shaoyi Du , Yue Gao

Large language models (LLMs) have shown significant potential in scientific disciplines such as biomedicine, particularly in hypothesis generation, where they can analyze vast literature, identify patterns, and suggest research directions.…

Computation and Language · Computer Science 2025-06-10 Guangzhi Xiong , Eric Xie , Corey Williams , Myles Kim , Amir Hassan Shariatmadari , Sikun Guo , Stefan Bekiranov , Aidong Zhang

Creating high-quality figures and visualizations for scientific papers is a time-consuming task that requires both deep domain knowledge and professional design skills. Despite over 2.5 million scientific papers published annually, the…

Artificial Intelligence · Computer Science 2026-01-09 Siyuan Huang , Yutong Gao , Juyang Bai , Yifan Zhou , Zi Yin , Xinxin Liu , Rama Chellappa , Chun Pong Lau , Sayan Nag , Cheng Peng , Shraman Pramanick

Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant documents. We close this gap with the Hierarchical Lexical Graph…

The emergence of generative AI models has dramatically expanded the availability and use of synthetic data across scientific, industrial, and policy domains. While these developments open new possibilities for data analysis, they also raise…

Machine Learning · Statistics 2026-03-06 Ahmad Abdel-Azim , Ruoyu Wang , Xihong Lin

Advances in artificial intelligence (AI) promise autonomous discovery, yet most systems still resurface knowledge latent in their training data. We present Sparks, a multi-modal multi-agent AI model that executes the entire discovery cycle…

Artificial Intelligence · Computer Science 2025-04-29 Alireza Ghafarollahi , Markus J. Buehler

Contemporary approaches to assisted scientific discovery use language models to automatically generate large numbers of potential hypothesis to test, while also automatically generating code-based experiments to test those hypotheses. While…

Artificial Intelligence · Computer Science 2025-09-23 Peter Jansen , Samiah Hassan , Ruoyao Wang

Previous works on Natural Language Generation (NLG) from structured data have primarily focused on surface-level descriptions of record sequences. However, for complex structured data, e.g., multi-row tables, it is often desirable for an…

Computation and Language · Computer Science 2020-09-25 Zhiyu Chen , Wenhu Chen , Hanwen Zha , Xiyou Zhou , Yunkai Zhang , Sairam Sundaresan , William Yang Wang

The field of hypothesis generation promises to reduce costs in neuroscience by narrowing the range of interventional studies needed to study various phenomena. Existing machine learning methods can generate scientific hypotheses from…

Machine Learning · Computer Science 2025-07-04 Zachary C. Brown , David Carlson

Data-driven social science research is inherently slow, relying on iterative cycles of observation, hypothesis generation, and experimental validation. While recent data-driven methods promise to accelerate parts of this process, they…

Large language models (LLMs) are increasingly expected to go beyond simple factual queries toward Deep Research-tasks that require decomposing questions into sub-problems, coordinating multi-step reasoning, and synthesizing evidence from…

Computation and Language · Computer Science 2025-09-03 Ziyi Xia , Kun Luo , Hongjin Qian , Zheng Liu

Empirical research in Natural Language Processing (NLP) has adopted a narrow set of principles for assessing hypotheses, relying mainly on p-value computation, which suffers from several known issues. While alternative proposals have been…

Computation and Language · Computer Science 2020-05-06 Erfan Sadeqi Azer , Daniel Khashabi , Ashish Sabharwal , Dan Roth

We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. HBG incorporates lexical, syntactic, semantic, and structural information…

cmp-lg · Computer Science 2008-02-03 Ezra Black , Fred Jelinek , John Lafferty , David M. Magerman , Robert Mercer , Salim Roukos

Large language models LLMs have transformed AI and achieved breakthrough performance on a wide range of tasks In science the most interesting application of LLMs is for hypothesis formation A feature of LLMs which results from their…

In an era of exponential scientific growth, identifying novel research ideas is crucial and challenging in academia. Despite potential, the lack of an appropriate benchmark dataset hinders the research of novelty detection. More…

Computation and Language · Computer Science 2025-06-02 Yan Liu , Zonglin Yang , Soujanya Poria , Thanh-Son Nguyen , Erik Cambria

Existing RAG benchmarks often overlook query difficulty, leading to inflated performance on simpler questions and unreliable evaluations. A robust benchmark dataset must satisfy three key criteria: quality, diversity, and difficulty, which…

Information Retrieval · Computer Science 2025-06-02 Jeongsoo Lee , Daeyong Kwon , Kyohoon Jin , Junnyeong Jeong , Minwoo Sim , Minwoo Kim

We explore story generation: creative systems that can build coherent and fluent passages of text about a topic. We collect a large dataset of 300K human-written stories paired with writing prompts from an online forum. Our dataset enables…

Computation and Language · Computer Science 2018-05-15 Angela Fan , Mike Lewis , Yann Dauphin

The vast amount of biomedical information available today presents a significant challenge for investigators seeking to digest, process, and understand these findings effectively. Large Language Models (LLMs) have emerged as powerful tools…

Computation and Language · Computer Science 2024-07-19 Alexander R. Pelletier , Joseph Ramirez , Irsyad Adam , Simha Sankar , Yu Yan , Ding Wang , Dylan Steinecke , Wei Wang , Peipei Ping

A plausible future mathematical claim must satisfy two constraints: it should follow the direction of prior work and respect the formal dependencies that constrain what can validly follow. Existing approaches typically model only one of…

Computation and Language · Computer Science 2026-05-29 David Busbib , Michael Werman