Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.10502 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917401285623808 |
|---|---|
| author | Lu, Haotian Mou, Yuchen Wu, Bingzhe |
| author_facet | Lu, Haotian Mou, Yuchen Wu, Bingzhe |
| contents | Content moderation in online platforms faces persistent challenges due to the evolving complexity of user-generated content and the limitations of traditional rule-based and machine learning approaches. While recent advances in large language models (LLMs) have enabled more sophisticated moderation via direct prompting or fine-tuning, these approaches often exhibit limited generalization, interpretability, and adaptability to unseen or ambiguous cases.
In this work, we propose a novel moderation framework that leverages analogical examples to enhance rule induction and decision reliability. Our approach integrates end-to-end optimization of analogical retrieval, rule generation, and moderation classification, enabling the dynamic adaptation of moderation rules to diverse content scenarios. Through comprehensive experiments, we demonstrate that our method significantly outperforms both rule-injected fine-tuning baselines and multi-stage static RAG pipelines in terms of moderation accuracy and rule quality. Further evaluations, including human assessments and external model generalization tests, confirm that our framework produces rules with better clarity, interpretability, and applicability. These findings show that analogical example-driven methods can advance robust, explainable, and generalizable content moderation in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10502 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs Lu, Haotian Mou, Yuchen Wu, Bingzhe Artificial Intelligence Content moderation in online platforms faces persistent challenges due to the evolving complexity of user-generated content and the limitations of traditional rule-based and machine learning approaches. While recent advances in large language models (LLMs) have enabled more sophisticated moderation via direct prompting or fine-tuning, these approaches often exhibit limited generalization, interpretability, and adaptability to unseen or ambiguous cases. In this work, we propose a novel moderation framework that leverages analogical examples to enhance rule induction and decision reliability. Our approach integrates end-to-end optimization of analogical retrieval, rule generation, and moderation classification, enabling the dynamic adaptation of moderation rules to diverse content scenarios. Through comprehensive experiments, we demonstrate that our method significantly outperforms both rule-injected fine-tuning baselines and multi-stage static RAG pipelines in terms of moderation accuracy and rule quality. Further evaluations, including human assessments and external model generalization tests, confirm that our framework produces rules with better clarity, interpretability, and applicability. These findings show that analogical example-driven methods can advance robust, explainable, and generalizable content moderation in real-world applications. |
| title | CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.10502 |