CoChat

LLMs for science: Usage for code generation and data analysis

Nejjar, Mohamed, Zacharias, Luca, Stiehle, Fabian, Weber, Ingo · 2025 · Journal of Software: Evolution and Process
Cited by 72

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Abstract

Large language models (LLMs) have been touted to enable increased productivity in many areas of today's work life. Scientific research as an area of work is no exception: The potential of LLM‐based tools to assist in the daily work of scientists has become a highly discussed topic across disciplines. However, we are only at the very onset of this subject of study. It is still unclear how the potential of LLMs will materialize in research practice. With this study, we give first empirical evidence on the use of LLMs in the research process. We have investigated a set of use cases for LLM‐based tools in scientific research and conducted a first study to assess to which degree current tools are helpful. In this position paper, we report specifically on use cases related to software engineering, specifically, on generating application code and developing scripts for data analytics and visualization. While we studied seemingly simple use cases, results across tools differ significantly. Our results highlight the promise of LLM‐based tools in general, yet we also observe various issues, particularly regarding the integrity of the output these tools provide.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1002/smr.2723

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 14

  1. 10.1287/isre.2023.ed.v34.n2 · DOI · Paper page
  2. 10.1371/journal.pdig.0000388 · DOI · Paper page
  3. HongZ AjithA PauloskiJ DuedeE ChardK FosterI.The diminishing returns of masked language models to science. In: Findings of the Association for Computational Linguistics: ACL 2023.Association for Computational LinguisticsACL;2023;Toronto Canada:1270‐1283.https://aclanthology.org/2023.findings-acl.82 · DOI · Paper page
  4. ChangY WangX WangJ et al.A survey on evaluation of large language models. arXiv preprint arXiv:230703109;2023.
  5. ChenM TworekJ JunH et al.Evaluating large language models trained on code. arXiv preprint arXiv:210703374;2021.
  6. AustinJ OdenaA NyeM et al.Program synthesis with large language models. arXiv preprint arXiv:210807732;2021.
  7. LaiY LiC WangY ZhangT ZhongR ZettlemoyerL YihW FriedD WangS YuT.DS‐1000: a natural and reliable benchmark for data science code generation. In: International Conference on Machine Learning PMLR;2023:18319‐18345.
  8. NiA YinP ZhaoY et al.L2CEval: evaluating language‐to‐code generation capabilities of large language models. arXiv preprint arXiv:230917446;2023.
  9. OuyangS ZhangJM HarmanM WangM.LLM is like a box of chocolates: the non‐determinism of ChatGPT in code generation. arXiv preprint arXiv:230802828;2023.
  10. HuangD BuQ ZhangJ XieX ChenJ CuiH.Bias assessment and mitigation in LLM‐based code generation. arXiv preprint arXiv:230914345;2023.
  11. PengS KalliamvakouE CihonP DemirerM.The impact of AI on developer productivity: evidence from GitHub Copilot. arXiv preprint arXiv:230206590;2023.
  12. FhGenie: The Fraunhofer‐Gesellschaft launches an internal AI chatbot. Fraunhofer Gesellschaft. Fraunhofer Gesellschaft Press Release Accessed 14‐11‐2023.https://www.fraunhofer.de/en/press/research-news/2023/august-2023/fhgenie-the-fraunhofer-gesellschaft-launches-an-internal-ai-chatbot.html;2023.
  13. WeberI LinkaH MertensD MuryshkinT OpgenoorthH LangerS.FhGenie: a custom confidentiality‐preserving chat AI for corporate and scientific use. In: Icsa'24: Proceedings of the IEEE International Conference on Software Architecture Software Architecture in Practice (SAIP) track IEEE;2024. · DOI
  14. ChowdheryA NarangS DevlinJ et al.PaLM: scaling language modeling with pathways. arXiv preprint arXiv:220402311;2022.

Cited by

See all 72

Metadata

Authors
Nejjar, M., Zacharias, L., Stiehle, F., & Weber, I.
Affiliations
School of Computation, Information and Technology Technical University of Munich Munich Germany
Venue
Journal of Software: Evolution and Process
Publisher
Wiley
Published
2024-09-12
Volume
37
Issue
1
ISSN
  • 2047-7473
  • 2047-7481
Cited by
72
References
13
Language
en

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.