{"ID":2837543,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.19083","arxiv_id":"2511.19083","title":"A Multi-Agent LLM Framework for Multi-Domain Low-Resource In-Context NER via Knowledge Retrieval, Disambiguation and Reflective Analysis","abstract":"In-context learning (ICL) with large language models (LLMs) has emerged as a promising paradigm for named entity recognition (NER) in low-resource scenarios. However, existing ICL-based NER methods suffer from three key limitations: (1) reliance on dynamic retrieval of annotated examples, which is problematic when annotated data is scarce; (2) limited generalization to unseen domains due to the LLM's insufficient internal domain knowledge; and (3) failure to incorporate external knowledge or resolve entity ambiguities. To address these challenges, we propose KDR-Agent, a novel multi-agent framework for multi-domain low-resource in-context NER that integrates Knowledge retrieval, Disambiguation, and Reflective analysis. KDR-Agent leverages natural-language type definitions and a static set of entity-level contrastive demonstrations to reduce dependency on large annotated corpora. A central planner coordinates specialized agents to (i) retrieve factual knowledge from Wikipedia for domain-specific mentions, (ii) resolve ambiguous entities via contextualized reasoning, and (iii) reflect on and correct model predictions through structured self-assessment. Experiments across ten datasets from five domains demonstrate that KDR-Agent significantly outperforms existing zero-shot and few-shot ICL baselines across multiple LLM backbones. The code and data can be found at https://github.com/MWXGOD/KDR-Agent.","short_abstract":"In-context learning (ICL) with large language models (LLMs) has emerged as a promising paradigm for named entity recognition (NER) in low-resource scenarios. However, existing ICL-based NER methods suffer from three key limitations: (1) reliance on dynamic retrieval of annotated examples, which is problematic when anno...","url_abs":"https://arxiv.org/abs/2511.19083","url_pdf":"https://arxiv.org/pdf/2511.19083v1","authors":"[\"Wenxuan Mu\",\"Jinzhong Ning\",\"Di Zhao\",\"Yijia Zhang\"]","published":"2025-11-24T13:23:34Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":606700,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2837543,"paper_url":"https://arxiv.org/abs/2511.19083","paper_title":"A Multi-Agent LLM Framework for Multi-Domain Low-Resource In-Context NER via Knowledge Retrieval, Disambiguation and Reflective Analysis","repo_url":"https://github.com/MWXGOD/KDR-Agent","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}