InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29829-29837
DOI: 10.1609/aaai.v40i35.40229 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhongyu Yang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Hallucination remains a critical challenge in large language models (LLMs), hindering the development of reliable multimodal LLMs (MLLMs). However, existing solutions often rely on human intervention or underutilize the agent's ability to autonomously mitigate hallucination. To address these limitations, we draw inspiration from the way humans make reliable decisions in the real world. In particular, they begin with introspective reasoning to reduce uncertainty and form an initial judgment, then rely on external verification from diverse perspectives to reach a final decision. Motivated by this cognitive paradigm, we propose InEx, a training-free, multi-agent framework designed to autonomously mitigate hallucination. InEx introduces internal introspective reasoning, guided by entropy-based uncertainty estimation, to improve the reliability of the decision agent's reasoning process. The agent first generates a response, which is then iteratively verified and refined through external cross-modal multi-agent collaboration with the editing agent and self-reflection agents, further enhancing reliability and mitigating hallucination. Extensive experiments show that InEx consistently outperforms existing methods, achieving 4%-27% gains on general and hallucination benchmarks, and demonstrating strong robustness.
Zitieren
APA
Yang, Z., Yuan, Y., Jiang, X., An, B., & Pang, W. (2026). InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29829-29837. https://doi.org/10.1609/aaai.v40i35.40229
Vancouver
Yang Z, Yuan Y, Jiang X, An B, Pang W. InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29829-29837. doi:10.1609/aaai.v40i35.40229
BibTeX
@article{Yang2026,
author = {Yang, Zhongyu and Yuan, Yingfang and Jiang, Xuanming and An, Baoyi and Pang, Wei},
title = {InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {35},
pages = {29829--29837},
doi = {10.1609/aaai.v40i35.40229}
}
EUVIMED