Pith

open record

sign in

arxiv: 2310.07984 · v1 · pith:EDR6AWMC · submitted 2023-10-12 · cs.AI · cs.CE

Large Language Models for Scientific Synthesis, Inference and Explanation

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:EDR6AWMCrecord.jsonopen to challenge →

classification cs.AI cs.CE
keywords languagelargescientificknowledgemodelslearningmachineexplanation
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs

    cs.LG 2026-06 unverdicted novelty 6.0

    Proposes SCSuff metric for evaluating LLM explanation sufficiency via model-generated alternative inputs, showing explanations are typically insufficient and predictable from hidden states.

  2. Large Language Model-Assisted Framework for BSM Model Building

    hep-ph 2026-06 unverdicted novelty 6.0

    An open-source framework that automates BSM Lagrangian construction, anomaly checks, and mass-matrix derivation from natural-language field specifications by using an LLM only as an orchestration layer over a determin...

  3. Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator

    cs.DL 2025-07 unverdicted novelty 4.0

    The paper proposes a four-role framework for LLMs in scientific innovation and reviews methods, benchmarks, and limitations across Assistant, Collaborator, Scientist, and Evaluator roles.

  4. From Text to Discovery: How Large Language Models Are Accelerating and Complicating Research Across Scientific and Humanistic Disciplines

    cs.DL 2026-06 unverdicted novelty 3.0

    LLMs accelerate research workflows from idea generation to writing but introduce challenges like hallucination, bias, opacity, and ten systemic risks requiring new governance frameworks.

  5. Are Researchers Being Replaced by Artificial Intelligence?

    cs.CY 2026-04 unverdicted novelty 3.0

    AI is shifting researchers from creators to curators of generated content, risking loss of intellectual ownership and genuine understanding of science.