CoChat

LLMs Will Always Hallucinate, and We Need to Live with This

Open access
Banerjee, Sourav, Agarwal, Ayushi, Singla, Saloni · 2025 · Lecture Notes in Networks and Systems

The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.

Overview

Integrity signals

Registry

Crossref · 10.1007/978-3-031-99965-9_39

Cites

36 of 36 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

Citations

Cites

Show all 36 references

Research works printed but not linked: 10

  1. Dahl, M., Magesh, V., Suzgun, M., Ho, D.E.: Large legal fictions: profiling legal hallucinations in large language models. J. Legal Anal. 14, 179–217 (2024)
  2. Huang, L., et al.: A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions. arXiv preprint arXiv:2311.05232 (2023) · arXiv
  3. Kang, H., Liu, X.-Y.: Deficiency of large language models in finance: an empirical examination of hallucination. arXiv preprint arXiv:2403.15884 (2024) · arXiv
  4. Khan, M.S., Umer, H.: ChatGPT in finance: applications, challenges, and solutions. Heliyon 10(5), e26859 (2024)
  5. Marcus, G., Davis, E.: GPT-3, Bloviator: OpenAI’s language generator has no idea what it’s talking about. MIT Technol. Rev. 123(6), 54–61 (2020)
  6. Nelson, E., Kollias, G., Das, P., Chaudhury, S., Dan, S.: Needle in the haystack for memory based large language models. arXiv preprint arXiv:2405.20329 (2024) · arXiv
  7. Rawte, V., Priya, P., Tonmoy, S.M.T.I., Zaman, S.M.M., Sheth, A., Das, A.: Exploring the relationship between LLM hallucinations and prompt linguistic nuances: readability, formality, and concreteness. arXiv preprint arXiv:2309.10922 (2023) · arXiv
  8. Sipser, M.: Introduction to the Theory of Computation. Third edition. Cengage Learning (2006)
  9. Turing, A.M.: On computable numbers, with an application to the Entscheidungs problem. Proc. Lond. Math. Soc. 42(2), 230–265 (1936)
  10. Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017) · arXiv

Cited by

See all 94

Metadata

Authors
Banerjee, S., Agarwal, A., & Singla, S.
Corresponding author
Banerjee, Sourav
Venue
Lecture Notes in Networks and Systems
Published
2025
Pages
624-648
ISSN
  • 2367-3370 (ISSN-L)
  • 2367-3389
OpenAlex
W4413328432
Cited by
93
References
27
Citations by year
2026: 46 · 2025: 41
FWCI
82.94
Type
conference paper
Language
en
Open access
Licence
Locations
  • Lecture notes in networks and systems (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by-nc-sa)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
Keywords
large language models, hallucinations, AI hallucination, Gödel's incompleteness theorems, undecidability, halting problem, information retrieval, intent classification, text generation, fact-checking, human oversight

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: LLMs Will Always Hallucinate, and We Need to Live with This. https://app.cochat.ai/papers/10.1007/978-3-031-99965-9_39
The paper
Banerjee, S., Agarwal, A., & Singla, S. (2025). LLMs Will Always Hallucinate, and We Need to Live with This. Lecture Notes in Networks and Systems. https://doi.org/10.1007/978-3-031-99965-9_39

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.