pith. sign in

arxiv: 2606.08723 · v2 · pith:YCB2G5T5new · submitted 2026-06-07 · 💻 cs.DL · cs.CY

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

Saleh Afroogh , Yasser Pouresmaeil , Yiming Xu , Kevin Chen , Abhejay Murali , Junfeng Jiao This is my paper

Pith reviewed 2026-06-27 17:21 UTC · model grok-4.3

classification 💻 cs.DL cs.CY
keywords large language modelsresearch workflowsscientific discoveryhallucinationreproducibilityresearcher autonomyAI biasinterdisciplinary governance
0
0 comments X

The pith

Large language models speed up research tasks from hypothesis generation to writing but add risks around hallucination, bias, and researcher control.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Large language models are integrated into academic work in the natural sciences, social sciences, and humanities to handle literature reviews, data analysis, and drafting. The review maps these uses and identifies a repeated outcome where the tools cut time on routine steps while creating problems with fabricated content, non-reproducible results, skewed training data, and black-box decisions. It further lists ten less-examined issues such as loss of independent judgment, AI-reinforced preconceptions, unclear credit for outputs, and uneven availability of the technology. The authors argue these patterns call for shared rules, stronger checks on outputs, and more work on making model decisions understandable.

Core claim

The paper establishes that large language models accelerate research workflows across disciplines from hypothesis generation and literature synthesis to data analysis and scientific writing, while simultaneously introducing technical challenges including hallucination, reproducibility failures, dataset bias, and model opacity, plus ten systemic risks such as erosion of researcher autonomy, AI-driven confirmation bias, authorship ambiguity, and unequal access that together require interdisciplinary governance frameworks, robust validation standards, and expanded explainability research.

What carries the argument

Cross-disciplinary mapping of LLM integration into research workflows that isolates a consistent acceleration pattern alongside a specific catalog of technical and systemic challenges.

If this is right

  • Routine research steps such as literature synthesis and data analysis become faster when large language models are applied.
  • Validation standards must be strengthened to counter hallucination and non-reproducibility in model-assisted outputs.
  • Interdisciplinary governance frameworks are required to manage authorship ambiguity and unequal access.
  • Expanded research on model explainability is needed to address opacity and related decision-making risks.
  • AI-driven confirmation bias may steer inquiry in ways that reduce diversity of hypotheses tested.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Widespread adoption could shift researcher time allocation toward higher-level interpretation and away from data handling.
  • Publishing venues may need explicit policies on disclosure of model assistance to maintain credit norms.
  • Controlled experiments that track actual hours saved versus error rates introduced would test the net workflow gain.
  • The same challenges could appear in non-academic knowledge work such as policy analysis or legal review.

Load-bearing premise

The existing studies on large language model use in research are representative enough across fields to support both a single consistent pattern and a precise list of ten underexplored challenges.

What would settle it

A new, systematic survey of published LLM applications in multiple disciplines that either finds no uniform acceleration effect or identifies a substantially different set of dominant risks.

read the original abstract

Large Language Models (LLMs) are rapidly reshaping academic research across the natural sciences, social sciences, and humanities, yet the scientific community lacks a comprehensive, cross-disciplinary account of how these tools are being integrated, what they deliver, and where they fall short. This paper addresses that gap by mapping their current state and outlining an agenda for their responsible integration into scientific research. Our analysis reveals a consistent pattern: LLMs meaningfully accelerate research workflows -- from hypothesis generation and literature synthesis to data analysis and scientific writing -- while introducing serious challenges related to hallucination, reproducibility, dataset bias, and model opacity. Beyond technical limitations, we identify ten underexplored challenges, including the erosion of researcher autonomy, AI-driven confirmation bias, authorship ambiguity, and unequal access to these technologies -- systemic risks that demand interdisciplinary governance frameworks, robust validation standards, and expanded explainability research.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper maps the integration of LLMs into research workflows across natural sciences, social sciences, and humanities. It asserts that LLMs accelerate hypothesis generation, literature synthesis, data analysis, and writing while introducing challenges such as hallucination, reproducibility, dataset bias, and model opacity. It further claims to identify ten underexplored systemic challenges (erosion of researcher autonomy, AI-driven confirmation bias, authorship ambiguity, unequal access, etc.) and calls for governance frameworks, validation standards, and explainability research.

Significance. A transparent, reproducible cross-disciplinary synthesis could usefully inform policy and practice on LLM adoption in research. The current manuscript, however, supplies no methodological basis for its central claims, so its potential contribution cannot be evaluated.

major comments (2)
  1. [Abstract] Abstract: The claim of a 'consistent pattern' and the derivation of a specific list of ten underexplored challenges rests on an unspecified literature-mapping process. No search criteria, inclusion/exclusion rules, coding scheme, or inter-rater process are described, rendering the asserted pattern and the precise list of challenges untraceable and non-replicable.
  2. [Abstract] Abstract: The representativeness assumption—that the reviewed body of literature is sufficient to support both the acceleration/challenge pattern and the exact enumeration of ten systemic risks—is load-bearing for the paper's conclusions but is not justified by any disclosed corpus-construction or weighting procedure.
minor comments (1)
  1. [Abstract] The abstract refers to 'our analysis' without indicating the number of papers, disciplines covered, or time window examined.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the careful reading and for identifying the need for greater transparency regarding our synthesis approach. We agree that the abstract and manuscript would benefit from explicit description of the literature review process. We address each major comment below and will incorporate revisions accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The claim of a 'consistent pattern' and the derivation of a specific list of ten underexplored challenges rests on an unspecified literature-mapping process. No search criteria, inclusion/exclusion rules, coding scheme, or inter-rater process are described, rendering the asserted pattern and the precise list of challenges untraceable and non-replicable.

    Authors: We acknowledge that the abstract does not describe the literature-mapping process in detail. The manuscript is framed as a cross-disciplinary perspective drawing on a broad narrative review of recent publications rather than a formal systematic review with PRISMA-style protocols. To address the concern, the revised manuscript will add a dedicated 'Approach and Scope' section (or subsection in the introduction) that specifies the primary sources consulted (arXiv, PubMed, Google Scholar, disciplinary journals), example search terms used, the time frame (primarily 2022–2024), and the thematic synthesis process by which the ten challenges were distilled from recurring issues in the literature. This addition will improve traceability while preserving the paper's perspective character. revision: yes

  2. Referee: [Abstract] Abstract: The representativeness assumption—that the reviewed body of literature is sufficient to support both the acceleration/challenge pattern and the exact enumeration of ten systemic risks—is load-bearing for the paper's conclusions but is not justified by any disclosed corpus-construction or weighting procedure.

    Authors: The paper does not assert statistical representativeness or exhaustiveness of the corpus; the 'consistent pattern' and list of ten challenges are presented as observed themes across a diverse but non-exhaustive sample of the emerging literature. We will revise the abstract and add a limitations paragraph to explicitly state that the review is not weighted or comprehensive and that the ten challenges are illustrative of prominent systemic issues rather than a definitive ranked enumeration. This clarification will reduce the load-bearing nature of any implicit representativeness claim. revision: yes

Circularity Check

0 steps flagged

No circularity: qualitative synthesis grounded in external literature

full rationale

This is a qualitative review paper with no derivations, equations, fitted parameters, predictions, or self-referential constructions. The central claims (consistent acceleration pattern and list of ten challenges) are presented as emerging from analysis of cited external literature across disciplines. No load-bearing step reduces by construction to the paper's own inputs, self-citations, or ansatzes. This is the normal non-circular outcome for a synthesis without internal mathematical or statistical machinery.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper rests on the domain assumption that a cross-disciplinary literature review can reliably surface consistent patterns and previously undocumented systemic risks; no free parameters or invented entities are introduced.

axioms (1)
  • domain assumption A cross-disciplinary literature review can identify consistent patterns and underexplored challenges in LLM use across fields.
    Invoked in the abstract as the basis for the analysis and the claim of ten underexplored challenges.

pith-pipeline@v0.9.1-grok · 5703 in / 1238 out tokens · 22175 ms · 2026-06-27T17:21:07.992982+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

158 extracted references · 123 canonical work pages · 4 internal anchors

  1. [1]

    Zhang et al

    Q. Zhang et al. Scientific large language models: A survey on biological & chemical domains.arXiv preprint, 2024. doi: 10.48550/arXiv.2401.14656

    work page doi:10.48550/arxiv.2401.14656 2024

  2. [2]

    Liang et al

    W. Liang et al. Mapping the increasing use of llms in scientific papers.arXiv preprint, 2024. doi: 10.48550/arXiv.2404.01268

    work page doi:10.48550/arxiv.2404.01268 2024

  3. [3]

    The impact of large language models on scientific discovery: a preliminary study using gpt-4

    Microsoft Research AI4Science and Microsoft Azure Quantum. The impact of large language models on scientific discovery: a preliminary study using gpt-4. arXiv, 2023

    2023

  4. [4]

    A. Ibanez. Intellectual cyborgs and the future of science.Trends in Cognitive Sciences, 27(9):785–787, Sep 2023. doi: 10.1016/j. tics.2023.06.004

    work page doi:10.1016/j 2023

  5. [5]

    Salvagno, F

    M. Salvagno, F. S. Taccone, and A. G. Gerli. Can artificial intelligence help for scientific writing?Critical Care, 27(1):75, Feb 2023. doi: 10.1186/s13054-023-04380-2

    work page doi:10.1186/s13054-023-04380-2 2023

  6. [7]

    Boyko et al

    J. Boyko et al. An interdisciplinary outlook on large language models for scientific research.arXiv preprint, 2023. doi: 10.48550/ arXiv.2311.04929

    arXiv 2023

  7. [8]

    McGinness, P

    L. McGinness, P. Baumgartner, E. Onyango, and Z. Lema. Highlighting case studies in llm literature review of interdisciplinary system science. InInterdisciplinary System Science, pages 29–43. 2025. doi: 10.1007/978-981-96-0348-0_3

    work page doi:10.1007/978-981-96-0348-0_3 2025

  8. [9]

    J. G. Meyer et al. Chatgpt and large language models in academia: opportunities and challenges.BioData Mining, 16(1):20, Jul

  9. [10]

    doi: 10.1186/s13040-023-00339-9

    work page doi:10.1186/s13040-023-00339-9

  10. [11]

    N. L. Rane, A. Tawde, S. P. Choudhary, and J. Rane. Contribution and performance of chatgpt and other large language models (llm) for scientific and research advancements: a double-edged sword.Open Access, 05(10), 2023. URLhttps://d1wqtxts1xzle7. cloudfront.net/106498559/Contribution_of_ChatGPT-libre.pdf

    arXiv 2023

  11. [12]

    Altmäe, A

    S. Altmäe, A. Sola-Leyva, and A. Salumets. Artificial intelligence in scientific writing: a friend or a foe?Reproductive BioMedicine Online, 47(1):3–9, Jul 2023. doi: 10.1016/j.rbmo.2023.04.009

    work page doi:10.1016/j.rbmo.2023.04.009 2023

  12. [13]

    Nejjar, L

    M. Nejjar, L. Zacharias, F. Stiehle, and I. Weber. Llms for science: Usage for code generation and data analysis.Journal of Software: Evolution and Process, Sep 2024. doi: 10.1002/smr.2723

    work page doi:10.1002/smr.2723 2024

  13. [14]

    NEJM AI , volume=

    W. Liang et al. Can large language models provide useful feedback on research papers? a large-scale empirical analysis.NEJM AI, 1 (8), Jul 2024. doi: 10.1056/AIoa2400196

    work page doi:10.1056/aioa2400196 2024

  14. [15]

    C. Si, D. Yang, and T. Hashimoto. Can llms generate novel research ideas? a large-scale human study with 100+ nlp researchers. arXiv preprint, 2024. doi: 10.48550/arXiv.2409.04109

    work page doi:10.48550/arxiv.2409.04109 2024

  15. [16]

    Elbadawi, H

    M. Elbadawi, H. Li, A. W. Basit, and S. Gaisford. The role of artificial intelligence in generating original scientific research. International Journal of Pharmaceutics, 652:123741, Mar 2024. doi: 10.1016/j.ijpharm.2023.123741

    work page doi:10.1016/j.ijpharm.2023.123741 2024

  16. [17]

    B. Wang, X. Zhang, S. Li, and Y. Wang. The practice of enhancing learning and scientific innovative abilities using llm-based ai tools. In2024 6th International Conference on Computer Science and Technologies in Education (CSTE), pages 166–170. IEEE, Apr

  17. [18]

    doi: 10.1109/CSTE62025.2024.00038

    work page doi:10.1109/cste62025.2024.00038 2024

  18. [19]

    Wang et al

    W. Wang et al. Scipip: An llm-based scientific paper idea proposer.arXiv preprint, 2024. doi: 10.48550/arXiv.2410.23166

    work page doi:10.48550/arxiv.2410.23166 2024

  19. [20]

    S. A. Lehr, A. Caliskan, S. Liyanage, and M. R. Banaji. Chatgpt as research scientist: Probing gpt’s capabilities as a research librarian, research ethicist, data generator, and data predictor.Proceedings of the National Academy of Sciences, 121(35), Aug 2024. doi: 10.1073/pnas.2404328121

    work page doi:10.1073/pnas.2404328121 2024

  20. [21]

    Zheng et al

    Y. Zheng et al. Large language models for scientific synthesis, inference and explanation.arXiv preprint, 2023. doi: 10.48550/ arXiv.2310.07984

    arXiv 2023

  21. [22]

    R. C. Hughes and A. van Heerden. Plos-llm: Can and should ai enable a new paradigm of scientific knowledge sharing?PLOS Digital Health, 3(4):e0000501, Apr 2024. doi: 10.1371/journal.pdig.0000501

    work page doi:10.1371/journal.pdig.0000501 2024

  22. [23]

    Birhane, A

    A. Birhane, A. Kasirzadeh, D. Leslie, and S. Wachter. Science in the age of large language models.Nature Reviews Physics, 5(5): 277–280, Apr 2023. doi: 10.1038/s42254-023-00581-4

    work page doi:10.1038/s42254-023-00581-4 2023

  23. [24]

    Wagle, S

    S. Wagle, S. Munikoti, A. Acharya, S. Smith, and S. Horawalavithana. Empirical evaluation of uncertainty quantification in retrieval-augmented language models for science.arXiv preprint, 2023. doi: 10.48550/arXiv.2311.09358. 32 From Text to Discovery: How Large Language Models Are Accelerating and Complicating Research Across Scientific and Humanistic Disciplines

    work page doi:10.48550/arxiv.2311.09358 2023

  24. [25]

    Mugaanyi, L

    J. Mugaanyi, L. Cai, S. Cheng employment, C. Lu, and J. Huang. Evaluation of large language model performance and reliability for citations and references in scholarly writing: Cross-disciplinary study.Journal of Medical Internet Research, 26:e52935, Apr

  25. [26]

    J.-Y. Park. Could chatgpt help you to write your next scientific paper?: concerns on research ethics related to usage of artificial intelligence tools.Journal of the Korean Association of Oral and Maxillofacial Surgeons, 49(3):105–106, Jun 2023. doi: 10.5125/ jkaoms.2023.49.3.105

    2023

  26. [27]

    Distinguishing Fact from Fiction: A Benchmark Dataset for Identifying Machine-Generated Scientific Papers in the LLM Era

    E. Mosca, M. H. I. Abdalla, P. Basso, M. Musumeci, and G. Groh. Distinguishing fact from fiction: A benchmark dataset for identifying machine-generated scientific papers in the llm era. InProceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023), pages 190–207, Stroudsburg, PA, USA, 2023. Association for Computational Ling...

    work page doi:10.18653/v1/2023.trustnlp-1.17 2023

  27. [28]

    R. Watkins. Guidance for researchers and peer-reviewers on the ethical use of large language models (llms) in scientific research workflows.AI and Ethics, 4(4):969–974, Nov 2024. doi: 10.1007/s43681-023-00294-5

    work page doi:10.1007/s43681-023-00294-5 2024

  28. [29]

    Ifargan, L

    T. Ifargan, L. Hafner, M. Kern, O. Alcalay, and R. Kishony. Autonomous llm-driven research — from data to human-verifiable research papers.NEJM AI, Dec 2024. doi: 10.1056/AIoa2400555

    work page doi:10.1056/aioa2400555 2024

  29. [30]

    C. Lu, C. Lu, R. T. Lange, J. Foerster, J. Clune, and D. Ha. The ai scientist: Towards fully automated open-ended scientific discovery. arXiv preprint, 2024. doi: 10.48550/arXiv.2408.06292

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2408.06292 2024

  30. [32]

    M. C. Ramos, C. J. Collison, and A. D. White. A review of large language models and autonomous agents in chemistry.arXiv preprint, 2024. doi: 10.48550/arXiv.2407.01603

    work page doi:10.48550/arxiv.2407.01603 2024

  31. [33]

    Schilling-Wilhelmi et al

    M. Schilling-Wilhelmi et al. From text to insight: Large language models for materials science data extraction.arXiv preprint, 2024. doi: 10.48550/arXiv.2407.16867

    work page doi:10.48550/arxiv.2407.16867 2024

  32. [35]

    K. M. Jablonka et al. 14 examples of how llms can transform materials science and chemistry: a reflection on a large language model hackathon.Digital Discovery, 2(5):1233–1250, 2023. doi: 10.1039/D3DD00113J

    work page doi:10.1039/d3dd00113j 2023

  33. [36]

    Zimmermann et al

    Y. Zimmermann et al. Reflections from the 2024 large language model (llm) hackathon for applications in materials science and chemistry.arXiv preprint, 2024. doi: 10.48550/arXiv.2411.15221

    work page doi:10.48550/arxiv.2411.15221 2024

  34. [37]

    Van Herck et al

    J. Van Herck et al. Assessment of fine-tuned large language models for real-world chemistry and material science applications. Chemical Science, 2024. doi: 10.1039/D4SC04401K

    work page doi:10.1039/d4sc04401k 2024

  35. [38]

    K. M. Jablonka, P. Schwaller, A. Ortega-Guerrero, and B. Smit. Leveraging large language models for predictive chemistry.Nature Machine Intelligence, 6(2):161–169, Feb 2024. doi: 10.1038/s42256-023-00788-1

    work page doi:10.1038/s42256-023-00788-1 2024

  36. [39]

    A. N. Rubungo, C. Arnold, B. P. Rand, and A. B. Dieng. Llm-prop: Predicting physical and electronic properties of crystalline solids from their text descriptions.arXiv preprint, 2023. doi: 10.48550/arXiv.2310.14029

    work page doi:10.48550/arxiv.2310.14029 2023

  37. [40]

    Zhang, Y

    H. Zhang, Y. Song, Z. Hou, S. Miret, and B. Liu. Honeycomb: A flexible llm-based agent system for materials science.arXiv preprint,

  38. [41]

    doi: 10.48550/arXiv.2409.00135

    work page doi:10.48550/arxiv.2409.00135

  39. [42]

    M. Lu, F. Gao, X. Tang, and L. Chen. Analysis and prediction in scr experiments using gpt-4 with an effective chain-of-thought prompting strategy.iScience, 27(4):109451, Apr 2024. doi: 10.1016/j.isci.2024.109451

    work page doi:10.1016/j.isci.2024.109451 2024

  40. [43]

    Kang and J

    Y. Kang and J. Kim. Chatmof: an artificial intelligence system for predicting and generating metal-organic frameworks using large language models.Nature Communications, 15(1):4705, Jun 2024. doi: 10.1038/s41467-024-48998-4

    work page doi:10.1038/s41467-024-48998-4 2024

  41. [44]

    H. Wang, K. Li, S. Ramsay, Y. Fehlis, E. Kim, and J. Hattrick-Simpers. Evaluating the performance and robustness of llms in materials science q&a and property predictions.arXiv preprint, 2024. doi: 10.48550/arXiv.2409.14572

    work page doi:10.48550/arxiv.2409.14572 2024

  42. [45]

    G. Lei, R. Docherty, and S. J. Cooper. Materials science in the era of large language models: a perspective.Digital Discovery, 3(7): 1257–1272, 2024. doi: 10.1039/D4DD00074A

    work page doi:10.1039/d4dd00074a 2024

  43. [46]

    L. Zhao, C. Edwards, and H. Ji. What a scientific language model knows and doesn’t know about chemistry. InNeurIPS 2023 AI for Science Workshop, 2023. URLhttps://openreview.net/forum?id=hSmn7BQZ2v

    2023

  44. [47]

    MohanaSundaram et al

    A. MohanaSundaram et al. Prevalence and usage trends of large language models in health science publications: A cross-sectional analysis.Preprint, Nov 2024. doi: 10.21203/rs.3.rs-5259782/v1. 33 From Text to Discovery: How Large Language Models Are Accelerating and Complicating Research Across Scientific and Humanistic Disciplines

    work page doi:10.21203/rs.3.rs-5259782/v1 2024

  45. [48]

    M. Sallam. The utility of chatgpt as an example of large language models in healthcare education, research and practice: Systematic review on the future perspectives and potential limitations.Preprint, Feb 2023. doi: 10.1101/2023.02.19.23286155

    work page doi:10.1101/2023.02.19.23286155 2023

  46. [49]

    Deng et al

    H. Deng et al. The current status and prospects of large language models in medical application and research.Chinese Journal of Academic Radiology, 7(4):292–300, Dec 2024. doi: 10.1007/s42058-024-00164-x

    work page doi:10.1007/s42058-024-00164-x 2024

  47. [50]

    J. K. Kim, M. Chua, M. Rickard, and A. Lorenzo. Chatgpt and large language model (llm) chatbots: The current state of acceptability and a proposal for guidelines on utilization in academic medicine.Journal of Pediatric Urology, 19(5):598–604, Oct 2023. doi: 10.1016/j.jpurol.2023.05.018

    work page doi:10.1016/j.jpurol.2023.05.018 2023

  48. [51]

    Bhattacharya, S

    M. Bhattacharya, S. Pal, S. Chatterjee, S.-S. Lee, and C. Chakraborty. Large language model to multimodal large language model: A journey to shape the biological macromolecules to biological sciences and medicine.Molecular Therapy-Nucleic Acids, 35(3): 102255, Sep 2024. doi: 10.1016/j.omtn.2024.102255

    work page doi:10.1016/j.omtn.2024.102255 2024

  49. [52]

    Telenti, M

    A. Telenti, M. Auli, B. L. Hie, C. Maher, S. Saria, and J. P. A. Ioannidis. Large language models for science and medicine.European Journal of Clinical Investigation, 54(6), Jun 2024. doi: 10.1111/eci.14183

    work page doi:10.1111/eci.14183 2024

  50. [53]

    S. P. Shashikumar and S. Nemati. A prospective comparison of large language models for early prediction of sepsis. InBiocomputing 2025, pages 109–120. WORLD SCIENTIFIC, Dec 2024. doi: 10.1142/9789819807024_0009

    work page doi:10.1142/9789819807024_0009 2025

  51. [54]

    Lu and U

    H. Lu and U. Naseem. Can large language models enhance predictions of disease progression? investigating through disease network link prediction. InProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17703–17715, Stroudsburg, PA, USA, 2024. Association for Computational Linguistics. doi: 10.18653/v1/2024.emnlp-main.980

    work page doi:10.18653/v1/2024.emnlp-main.980 2024

  52. [55]

    Reinisch, J

    M. Reinisch, J. He, C. Liao, S. A. Siddiqui, and B. Xiao. Ctp-llm: Clinical trial phase transition prediction using large language models.arXiv preprint, 2024. doi: 10.48550/arXiv.2408.10995

    work page doi:10.48550/arxiv.2408.10995 2024

  53. [56]

    Ben Shoham and N

    O. Ben Shoham and N. Rappoport. Cpllm: Clinical prediction with large language models.arXiv preprint, 2024. doi: 10.48550/ arXiv.2309.11295

    arXiv 2024

  54. [57]

    Y. Kim, X. Xu, D. McDuff, C. Breazeal, and H. W. Park. Health-llm: Large language models for health prediction via wearable sensor data.arXiv preprint, 2024. doi: 10.48550/arXiv.2401.06866

    work page doi:10.48550/arxiv.2401.06866 2024

  55. [58]

    S. M. Tharayil, A. Alnajashi, A. Al-Ahamri, and M. Shahada. A framework for predicting pandemic severity and mortality using generative ai and llms. InSPE International Health, Safety, Environment and Sustainability Conference and Exhibition. SPE, Sep

  56. [59]

    doi: 10.2118/220429-MS

    work page doi:10.2118/220429-ms

  57. [60]

    Jin et al

    M. Jin et al. Prollm: Protein chain-of-thoughts enhanced llm for protein-protein interaction prediction.Preprint, Apr 2024. doi: 10.1101/2024.04.18.590025

    work page doi:10.1101/2024.04.18.590025 2024

  58. [61]

    Y. Xiao, E. Sun, Y. Jin, Q. Wang, and W. Wang. Proteingpt: Multimodal llm for protein property prediction and structure understanding.arXiv preprint, 2024. doi: 10.48550/arXiv.2408.11363

    work page doi:10.48550/arxiv.2408.11363 2024

  59. [62]

    Peng et al

    C. Peng et al. A study of generative large language model for medical research and healthcare.NPJ Digital Medicine, 6(1):210, Nov

  60. [63]

    doi: 10.1038/s41746-023-00958-w

    work page doi:10.1038/s41746-023-00958-w

  61. [64]

    Wysocki et al

    O. Wysocki et al. An llm-based knowledge synthesis and scientific reasoning framework for biomedical discovery.arXiv preprint,

  62. [65]

    doi: 10.48550/arXiv.2406.18626

    work page doi:10.48550/arxiv.2406.18626

  63. [66]

    S. Pal, M. Bhattacharya, S.-S. Lee, and C. Chakraborty. A domain-specific next-generation large language model (llm) or chatgpt is required for biomedical engineering and research.Annals of Biomedical Engineering, 52(3):451–454, Mar 2024. doi: 10.1007/ s10439-023-03306-x

    2024

  64. [67]

    Eggmann, R

    F. Eggmann, R. Weiger, N. U. Zitzmann, and M. B. Blatz. Implications of large language models such as chatgpt for dental medicine. Journal of Esthetic and Restorative Dentistry, 35(7):1098–1102, Oct 2023. doi: 10.1111/jerd.13046

    work page doi:10.1111/jerd.13046 2023

  65. [68]

    B. V. Janssen, G. Kazemier, and M. G. Besselink. The use of chatgpt and other large language models in surgical science.BJS Open, 7(2), Mar 2023. doi: 10.1093/bjsopen/zrad032

    work page doi:10.1093/bjsopen/zrad032 2023

  66. [69]

    Chakraborty, S

    C. Chakraborty, S. Pal, M. Bhattacharya, and Md. A. Islam. Chatgpt or llms can provide treatment suggestions for critical patients with antibiotic-resistant infections: a next-generation revolution for medical science?International Journal of Surgery, 110(3): 1829–1831, Mar 2024. doi: 10.1097/JS9.0000000000000987

    work page doi:10.1097/js9.0000000000000987 2024

  67. [70]

    M. Sallam. Chatgpt utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns.Healthcare, 11(6):887, Mar 2023. doi: 10.3390/healthcare11060887

    work page doi:10.3390/healthcare11060887 2023

  68. [71]

    A. Alaa, R. V. Phillips, E. Kıcıman, L. B. Balzer, M. van der Laan, and M. Petersen. Large language models as co-pilots for causal inference in medical studies.arXiv preprint, 2024. doi: 10.48550/arXiv.2407.19118. 34 From Text to Discovery: How Large Language Models Are Accelerating and Complicating Research Across Scientific and Humanistic Disciplines

    work page doi:10.48550/arxiv.2407.19118 2024

  69. [72]

    C. Gao, T. Fu, and J. Sun. Lint: Llm interaction network for clinical trial outcome prediction. InArtificial Intelligence and Data Science for Healthcare: Bridging Data-Centric AI and People-Centric Healthcare, 2024. URLhttps://openreview.net/forum? id=c1LTf7ZsBP

    2024

  70. [73]

    Sun et al

    D. Sun et al. Outcome prediction using multi-modal information: Integrating large language model-extracted clinical information and image analysis.Cancers, 16(13):2402, Jun 2024. doi: 10.3390/cancers16132402

    work page doi:10.3390/cancers16132402 2024

  71. [74]

    Bzdok, A

    D. Bzdok, A. Thieme, O. Levkovskyy, P. Wren, T. Ray, and S. Reddy. Data science opportunities of large language models for neuroscience and biomedicine.Neuron, 112(5):698–717, Mar 2024. doi: 10.1016/j.neuron.2024.01.016

    work page doi:10.1016/j.neuron.2024.01.016 2024

  72. [75]

    Luo et al

    X. Luo et al. Large language models surpass human experts in predicting neuroscience results.Nature Human Behaviour, Nov 2024. doi: 10.1038/s41562-024-02046-9

    work page doi:10.1038/s41562-024-02046-9 2024

  73. [76]

    L. P. A. Simons, P. K. Murukannaiah, and M. A. Neerincx. Designing and evaluating an llm-based health ai research assistant for hypertension self-management; using health claims metadata criteria. InResilience Through Digital Innovation: Enabling the Twin Transition, pages 283–298. University of Maribor Press, May 2024. doi: 10.18690/um.fov.4.2024.16

    work page doi:10.18690/um.fov.4.2024.16 2024

  74. [77]

    D. H. Solomon, K. D. Allen, P. Katz, A. H. Sawalha, and E. Yelin. Chatgpt, et al ...artificial intelligence, authorship, and medical publishing.ACR Open Rheumatology, 5(6):288–289, Jun 2023. doi: 10.1002/acr2.11538

    work page doi:10.1002/acr2.11538 2023

  75. [78]

    Abu-Jeyyab, S

    M. Abu-Jeyyab, S. Alrosan, and I. Alkhawaldeh. Harnessing large language models in medical research and scientific writing: A closer look to the future.High Yield Medical Reviews, 1(2), Dec 2023. doi: 10.59707/hymrFBYA5348

    work page doi:10.59707/hymrfbya5348 2023

  76. [79]

    Chakraborty, M

    C. Chakraborty, M. Bhattacharya, and S.-S. Lee. Artificial intelligence enabled chatgpt and large language models in drug target discovery, drug discovery, and development.Molecular Therapy-Nucleic Acids, 33:866–868, Sep 2023. doi: 10.1016/j.omtn.2023. 08.009

    work page doi:10.1016/j.omtn.2023 2023

  77. [80]

    Salami, B

    H. Salami, B. Smith-Goettler, and V. Yadav. Can foundational large language models assist with conducting pharmaceuticals manufacturing investigations?arXiv preprint, 2024. doi: 10.48550/arXiv.2404.15578

    work page doi:10.48550/arxiv.2404.15578 2024

  78. [81]

    S. Pal, M. Bhattacharya, Md. A. Islam, and C. Chakraborty. Chatgpt or llm in next-generation drug discovery and development: Pharmaceutical and biotechnology companies can make use of the artificial intelligence (ai)-based device for a faster way of drug discovery and development.International Journal of Surgery, Sep 2023. doi: 10.1097/JS9.0000000000000719

    work page doi:10.1097/js9.0000000000000719 2023

  79. [82]

    Chakraborty, M

    C. Chakraborty, M. Bhattacharya, S. Pal, and Md. A. Islam. Generative ai in drug discovery and development: the next revolution of drug discovery and development would be directed by generative ai.Annals of Medicine & Surgery, 86(10):6340–6343, Oct 2024. doi: 10.1097/MS9.0000000000002438

    work page doi:10.1097/ms9.0000000000002438 2024

  80. [83]

    Zheng et al

    Y. Zheng et al. Large language models in drug discovery and development: From disease mechanisms to clinical trials.arXiv preprint, 2024

    2024

Showing first 80 references.