paper-with-me

Papers

Large Language Models for Scientific Synthesis, Inference and Explanation

2023-10-12 · Yizhen Zheng, Huan Yee Koh, Jiaxin Ju, Anh T. N. Nguyen, Lauren T. May, Geoffrey I. Webb, Shirui Pan

Large language models are a form of artificial intelligence systems whose primary knowledge consists of the statistical patterns, semantic relationships, and syntactical structures of language1. Despite their limited forms of "knowledge", these systems are adept at numerous complex tasks including creative writing, storytelling, translation, question-answering, summarization, and computer code generation. However, they have yet to demonstrate advanced applications in natural science. Here we show how large language models can perform scientific synthesis, inference, and explanation. We present a method for using general-purpose large language models to make inferences from scientific datasets of the form usually associated with special-purpose machine learning algorithms. We show that the large language model can augment this "knowledge" by synthesizing from the scientific literature. When a conventional machine learning system is augmented with this synthesized and inferred knowledge it can outperform the current state of the art across a range of benchmark tasks for predicting molecular properties. This approach has the further advantage that the large language model can explain the machine learning system's predictions. We anticipate that our framework will open new avenues for AI to accelerate the pace of scientific discovery.

📄 PDF Abstract BibTeX arXiv:2310.07984

Code (1)

zyzisastudyreallyhardguy/llm4sd 공식 구현 pytorch

Tasks

Code GenerationLanguage ModelingLanguage ModellingLarge Language ModelQuestion Answeringscientific discovery

Similar Papers 제목 키워드 기반

Large Language Models as Evaluators for Scientific Synthesis

2024-07-03 · Julia Evans, Jennifer D'Souza, Sören Auer

Our study explores how well the state-of-the-art Large Language Models (LLMs), like GPT-4 and Mistral, can assess the quality of scientific summaries or, more fittingly, scientific syntheses, comparing their evaluations …

SciNets: Graph-Constrained Multi-Hop Reasoning for Scientific Literature Synthesis

2025-12-28 · Sauhard Dubey arxiv

Cross-domain scientific synthesis requires connecting mechanistic explanations across fragmented literature, a capability that remains challenging for both retrieval-based systems and unconstrained language models. While…

Question Answering

Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration

2021-07-25 · Marco Valentino, Mokanarangan Thayaparan, Deborah Ferreira, André Freitas

Regenerating natural language explanations in the scientific domain has been proposed as a benchmark to evaluate complex multi-hop and explainable inference. In this context, large language models can achieve state-of-th…

Multi-hop Question AnsweringNatural Language InferenceQuestion Answering

Leveraging large language models for nano synthesis mechanism explanation: solid foundations or mere conjectures?

2024-07-12 · Yingming Pu, Liping Huang, Tao Lin, Hongyu Chen

With the rapid development of artificial intelligence (AI), large language models (LLMs) such as GPT-4 have garnered significant attention in the scientific community, demonstrating great potential in advancing scientifi…

Logical ReasoningMultiple-choiceProperty Predictionscientific discovery

Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI

2022-05-03 · Marco Valentino, André Freitas

A fundamental research goal for Explainable AI (XAI) is to build models that are capable of reasoning through the generation of natural language explanations. However, the methodologies to design and evaluate explanation…

Explainable Artificial Intelligence (XAI)Philosophy