[2602.01031] HalluHard: A Hard Multi-Turn Hallucination Benchmark

Support arXiv on Cornell Giving Day!

We're celebrating 35 years of open science - with YOUR support! Your generosity has helped arXiv thrive for three and a half decades. Give today to help keep science open for ALL for many years to come.

Donate!

-->

Computer Science > Artificial Intelligence

arXiv:2602.01031 (cs)

[Submitted on 1 Feb 2026]

Title:HalluHard: A Hard Multi-Turn Hallucination Benchmark

Authors:Dongyang Fan, Sebastien Delsad, Nicolas Flammarion, Maksym Andriushchenko<br>View a PDF of the paper titled HalluHard: A Hard Multi-Turn Hallucination Benchmark, by Dongyang Fan and 3 other authors

View PDF<br>HTML (experimental)

Abstract:Large language models (LLMs) still produce plausible-sounding but ungrounded factual claims, a problem that worsens in multi-turn dialogue as context grows and early errors cascade. We introduce $\textbf{HalluHard}$, a challenging multi-turn hallucination benchmark with 950 seed questions spanning four high-stakes domains: legal cases, research questions, medical guidelines, and coding. We operationalize groundedness by requiring inline citations for factual assertions. To support reliable evaluation in open-ended settings, we propose a judging pipeline that iteratively retrieves evidence via web search. It can fetch, filter, and parse full-text sources (including PDFs) to assess whether cited material actually supports the generated content. Across a diverse set of frontier proprietary and open-weight models, hallucinations remain substantial even with web search ($\approx 30\%$ for the strongest configuration, Opus-4.5 with web search), with content-grounding errors persisting at high rates. Finally, we show that hallucination behavior is shaped by model capacity, turn position, effective reasoning, and the type of knowledge required.

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

Cite as:<br>arXiv:2602.01031 [cs.AI]

(or<br>arXiv:2602.01031v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2602.01031

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Dongyang Fan [view email]<br>[v1]<br>Sun, 1 Feb 2026 05:35:07 UTC (1,366 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled HalluHard: A Hard Multi-Turn Hallucination Benchmark, by Dongyang Fan and 3 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context: cs.AI

next >

new<br>recent<br>| 2026-02

Change to browse by:

cs<br>cs.CL

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

Links to Code Toggle

Papers with Code (What is Papers with Code?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)