‘Fighting fire with fire’ — using LLMs to combat LLM hallucinations (2024)

Table of Contents
Access options Additional access options: References Competing Interests Related Articles Subjects Latest on: Jobs Related Articles Subjects Sign up to Nature Briefing References
  • NEWS AND VIEWS

The number of errors produced by an LLM can be reduced by grouping its outputs into semantically similar clusters. Remarkably, this task can be performed by a second LLM, and the method’s efficacy can be evaluated by a third.

    By
  • Karin Verspoor0
  1. Karin Verspoor

    1. Karin Verspoor is in the School of Computing Technologies, RMIT University, Melbourne, Victoria 3000, Australia and in the School of Computing and Information Systems, University of Melbourne, Melbourne, Victoria 3010, Australia.

    View author publications

    You can also search for this author in PubMed Google Scholar

  • Twitter
  • Facebook
  • Email

Text-generation systems powered by large language models (LLMs) have been enthusiastically embraced by busy executives and programmers alike, because they provide easy access to extensive knowledge through a natural conversational interface. Scientists too have been drawn to both using and evaluating LLMs — finding applications for them in drug discovery1, in materials design2 and in proving mathematical theorems3. A key concern for such uses relates to the problem of ‘hallucinations’, in which the LLM responds to a question (or prompt) with text that seems like a plausible answer, but is factually incorrect or irrelevant4. How often hallucinations are produced, and in what contexts, remains to be determined, but it is clear that they occur regularly and can lead to errors and even harm if undetected. In a paper in Nature, Farquhar et al.5 tackle this problem by developing a method for detecting a specific subclass of hallucinations, termed confabulations.

Access options

Access through your institution

Change institution

Buy or subscribe

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

$29.99 /30days

cancel any time

Learn more

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Nature 630, 569-570 (2024)

doi: https://doi.org/10.1038/d41586-024-01641-0

References

  1. Vert, J.-P. Nature Biotechnol. 41, 750–751 (2023).

    Article PubMed Google Scholar

  2. Jablonka, K. M. et al. Digit. Discov. 2, 1233–1250 (2023).

    Article PubMed Google Scholar

  3. Frieder, S. et al. Mathematical capabilities of ChatGPT. In Proc. NeurIPS 36 (eds Oh, A. et al.) (NIPS, 2023).

    Google Scholar

  4. Hicks, M. T., Humphries, J. & Slater, J. Ethics Inf. Technol. 26, 38 (2024).

    Article Google Scholar

  5. Farquhar, S., Kossen, J., Kuhn, L. & Gal, Y. Nature 630, 625–630 (2024).

    Article Google Scholar

  6. Firth, J. R. Studies in Linguistic Analysis (Blackwell, 1957).

    Google Scholar

  7. Landauer, T. K. & Dumais, S. T. Psych. Rev. 104, 211–240 (1997).

    Article Google Scholar

  8. Bender, E. M. & Koller, A. in Proc. 58th Ann. Meet. ACL 5185–5198 (Association for Computational Linguistics, 2020).

    Google Scholar

  9. Mitchell, M. & Krakauer, D. C. Proc. Natl Acad. Sci. USA 120, e2215907120 (2023).

    Article PubMed Google Scholar

    See Also
    Israeli Military Spokesman: Gaza Needs New Leadership to Keep Hamas Out

  10. Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q. & Artzi, Y. In 8th Int.Conf.Learning Represent. (ICLR, 2020); available at https://openreview.net/forum?id=SkeHuCVFDr

    Google Scholar

  11. Wang, L. L. et al. In Proc. 61st Ann. Meet. ACL Vol. 1, 9871–9889 (Association for Computational Linguistics, 2023).

    Google Scholar

  12. Sun, T., He, J., Qiu, X. & Huang, X. In Proc. 2022 Conf. Empirical Methods in Natural Language Processing 3726–3739 (Association for Computational Linguistics, 2022).

    Google Scholar

  13. Koike, R., Kaneko, M. & Okazaki, N. Proc. AAAI Conf. Artificial Intell. 38, 21258–21266 (AAAI, 2024).

    Article Google Scholar

  14. Li, Y. et al. Preprint at arXiv https://doi.org/10.48550/arXiv.2405.12689 (2024).

  15. Taloni, A., Scorcia, V. & Giannaccare, G. Eye 38, 397–400 (2024).

    Article PubMed Google Scholar

  16. Zhang, Y. et al. Detection vs. Anti-detection: Is Text Generated by AI Detectable? In Wisdom, Well-Being, Win-Win (eds Sserwanga, I. et al.) Lecture Notes in Computer Science Vol. 14596 (Springer, 2024).

    Google Scholar

Download references

Competing Interests

K.V. has received speaker fees and travel reimbursem*nt for presentations on Artificial Intelligence, Natural Language Processing/LLMs, and AI in Health care; research funding from the Australian Research Council, the Australian National Health and Medical Research Council, and the Medical Research Futures Fund, and has research partnerships with Elsevier BV. K.V. is co-founder and Victoria Node Lead of the Australian Alliance for Artificial Intelligence in Healthcare; and a member of the Standards Australia Committee, IT-014-21, AI in Healthcare.

Related Articles

  • Read the paper: Detecting hallucinations in large language models using semantic entropy

  • Online tools help large language models to solve problems through reasoning

  • Large language models help computer programs to evolve

Subjects

  • Machine learning
  • Computer science

Latest on:

Not all ‘open source’ AI models are actually open: here’s a ranking News 19 JUN 24
Computational design of soluble and functional membrane protein analogues Article 19 JUN 24
Detecting hallucinations in large language models using semantic entropy Article 19 JUN 24
Experiment-free exoskeleton assistance via learning in simulation Article 12 JUN 24

‘Fighting fire with fire’ — using LLMs to combat LLM hallucinations (10)

Jobs

  • Research Postdoctoral Fellow - MD

    Houston, Texas (US)

    Baylor College of Medicine (BCM)

    ‘Fighting fire with fire’ — using LLMs to combat LLM hallucinations (11)

  • Postdoctoral position for EU project ARTiDe: A novel regulatory T celltherapy for type 1 diabetes

    Development of TCR-engineered Tregs for T1D. Single-cell analysis, evaluate TCRs. Join INEM's cutting-edge research team.

    Paris, Ile-de-France (FR)

    French National Institute for Health Research (INSERM)

    ‘Fighting fire with fire’ — using LLMs to combat LLM hallucinations (12)

  • Postdoc or PhD position: the biology of microglia in neuroinflammatory disease

    Join Our Team! Investigate microglia in neuroinflammation using scRNAseq and genetic tools. Help us advance CNS disease research at INEM!

    Paris, Ile-de-France (FR)

    French National Institute for Health Research (INSERM)

    ‘Fighting fire with fire’ — using LLMs to combat LLM hallucinations (13)

  • Postdoctoral Researcher Positions in Host-Microbiota/Pathogen Interaction

    Open postdoctoral positions in host microbiota/pathogen interaction requiring expertise in either bioinformatics, immunology or cryoEM.

    Paris, Ile-de-France (FR)

    French National Institute for Health Research (INSERM)

    ‘Fighting fire with fire’ — using LLMs to combat LLM hallucinations (14)

  • CMU - CIMR Joint Invitation for Global Outstanding Talents

    Basic medicine, biology, pharmacy, public health and preventive medicine, nursing, biomedical engineering...

    Beijing (CN)

    Capital Medical University - Chinese Institutes for Medical Research, Beijing

    ‘Fighting fire with fire’ — using LLMs to combat LLM hallucinations (15)

Access through your institution

Change institution

Buy or subscribe

Related Articles

  • Read the paper: Detecting hallucinations in large language models using semantic entropy

  • Online tools help large language models to solve problems through reasoning

  • Large language models help computer programs to evolve

Subjects

  • Machine learning
  • Computer science

Sign up to Nature Briefing

An essential round-up of science news, opinion and analysis, delivered to your inbox every weekday.

‘Fighting fire with fire’ — using LLMs to combat LLM hallucinations (2024)

References

Top Articles
15 Most Popular Christmas Cookie Recipes | Swanky Recipes - Simple tasty food recipes
Arancini Rice Balls Recipe (VIDEO)
Jeffrey Dahmer's Drawings
Jeffrey Dahmer Photos In Drawer
washington, DC for sale "20020" - craigslist
Serie A 2023/24 Preview & Predictions: Where Will Every Club Land?
Jet Ski Rental Conneaut Lake Pa
Dyi Urban Dictionary
Craigs List Tulsa Ok
Consecrate World Stellaris
Latest Posts
Italian Bread Recipe - Top Recipes
28 Gluten-Free Meal Prep Recipes
Article information

Author: Francesca Jacobs Ret

Last Updated:

Views: 5673

Rating: 4.8 / 5 (48 voted)

Reviews: 95% of readers found this page helpful

Author information

Name: Francesca Jacobs Ret

Birthday: 1996-12-09

Address: Apt. 141 1406 Mitch Summit, New Teganshire, UT 82655-0699

Phone: +2296092334654

Job: Technology Architect

Hobby: Snowboarding, Scouting, Foreign language learning, Dowsing, Baton twirling, Sculpting, Cabaret

Introduction: My name is Francesca Jacobs Ret, I am a innocent, super, beautiful, charming, lucky, gentle, clever person who loves writing and wants to share my knowledge and understanding with you.