Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator
Identifying faithfulness hallucinations in LLM-generated outputs remains challenging due to the scarcity of high-quality annotated data. This paper introduces Hallucination Self-Play (HSP), a framework where a detector and generator bootstrap each other. The detector is fine-tuned on human labels, then used as a reward model to train the generator via RLAIF to produce harder-to-detect hallucinations. The evolved generator's outputs further optimize the detector via rule-based RL. Experiments on RAGTruth and two model families show a small LLM can match or outperform advanced LLMs without external supervision.
-->
[Submitted on 8 Jul 2026]
Title:Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator
View a PDF of the paper titled Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator, by Shiping Yang and 6 other authors
View PDF HTML (experimental)
Abstract:Identifying faithfulness hallucinations in LLM-generated outputs remains challenging due to the scarcity of high-quality annotated data. Recent work relies on advanced LLMs to synthesize training data, including rationales, labels, and hallucinated claims. However, these methods treat the generator as a static component, limiting iterative improvement of the detector. To address this limitation, we introduce Hallucination Self-Play (HSP), a novel framework that enables the detector to bootstrap with an evolved generator. HSP involves two roles initialized from the same base model, a detector that assesses the faithfulness of model outputs, and a generator that produces increasingly hard-to-detect hallucinated responses. Specifically, the detector is first fine-tuned on human-labeled data and then employed as a reward model to train the generator via reinforcement learning from AI feedback (RLAIF). In turn, the evolved generator synthesizes hallucination data to further optimize the detector through rule-based reinforcement learning. Experiments on RAGTruth benchmark and two model families demonstrate that the proposed framework can progressively enhance a small LLM to match or even outperform advanced LLMs without external supervision. Our code is available at this https URL .
Comments: Accepted to COLM 2026. Camera-ready version to appear
Subjects:
Computation and Language (cs.CL); Machine Learning (cs.LG)
Cite as: arXiv:2607.07993 [cs.CL]
(or arXiv:2607.07993v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2607.07993
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Shiping Yang [view email] [v1] Wed, 8 Jul 2026 23:54:36 UTC (160 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator, by Shiping Yang and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-07
Change to browse by:
cs cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
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?)
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? | Disable MathJax (What is MathJax?)