Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations
Leonardo Ranaldi, Federico Ranaldi, Fabio Massimo Zanzotto, Barry Haddow, Alexandra Birch
Abstract
Retrieval-augmented generation (RAG) is key to improving large language models (LLMs) in systematically accessing richer factual knowledge. Yet, using RAG mechanisms brings intrinsic challenges, as LLMs must deal with conflicting knowledge, especially in multilingual retrieval, where the heterogeneity of knowledge retrieved may deliver different outlooks. To make RAG more analytical, critical and grounded, we introduce Dialectic-RAG (D-RAG), a modular approach guided by Argumentative Explanations, i.e., structured reasoning process that systematically evaluates retrieved information by comparing, contrasting, and resolving conflicting perspectives. Given a query and a set of multilingual related documents, D-RAG selects and exemplifies relevant knowledge for delivering dialectic explanations that, by critically weighing opposing arguments and filtering extraneous content, clearly determine the final response. We show the impact of our framework both as an incontext learning strategy and for constructing demonstrations to instruct smaller models. Our experiments demonstrate that D-RAG significantly improves RAG approaches, requiring low-impact computational effort and providing robustness to knowledge perturbations. 英格兰有多少位女王 [1] [英国曾有 13 位君主... Retrieval Augmented LLM Baseline Dialectic RAG -[3] states that eight queens ruled the Kingdom of England, naming Matilda, Lady Jane Grey, Mary I, Elizabeth I, Mary II, Anne, Victoria, and Elizabeth II. - [4] focuses specifically on Queen Anne, who ruled from 1702 and became the first monarch of the UK in 1707 following the union of England and Scotland. -[1] outlines the formation of the UK and mention 13 monarchs. -[5] mentions Elizabeth II and her rule over the UK but does not address the total number of queens in England. -Doc [3]: Claims there were eight queens in England's history. (Relevant): -Doc [4]: Discusses Queen Anne's reign and her role as the monarch when England and Scotland unified in 1707. (Partially Relevant) -Doc [1]: Explains the timeline of the United Kingdom's formation but does not reference the specific number of queens. (Partially Relevant) -Doc [5]: Mentions Elizabeth II's reign over the United Kingdom but focuses on her role in the Commonwealth. (Irrelevant) [3] In less than 200 years, eight queens ruled the Kingdom of England.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext aa55a22c-9e08-44c9-a7cf-8b6229f9c2bcCited by top-tier papers4
- Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAGDayeon Ki, Marine Carpuat, Paul McNamee, Daniel Khashabi et al.ICML 2026 · 7 citations
- Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time MitigationBo Li, Zhenghua Xu, Rui XieAAAI 2026
- Agentic Oversight via Dialectic ReasoningLeonardo Ranaldi, Federico RanaldiACL 2026
- Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-AgentGiulia Pucci, Leonardo RanaldiEMNLP 2025
Builds on12
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
- Large Language Models Can Be Easily Distracted by Irrelevant ContextFreda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales et al.ICML 2023 · 970 citations
- Making Retrieval-Augmented Language Models Robust to Irrelevant ContextOri Yoran, Tomer Wolfson, Ori Ram, Jonathan BerantICLR 2024 · 361 citations
- Active Retrieval Augmented GenerationZhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun et al.EMNLP 2023 · 315 citations
Related papers
- HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented GenerationPei Liu, Xin Liu, Ruoyu Yao, Junming Liu et al.ACM MM 2025 · 27 citations
- Disco-RAG: Discourse-Aware Retrieval-Augmented GenerationDongqi Liu, Hang Ding, Qiming Feng, Xurong Xie et al.ACL 2026
- A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented GenerationShiyu Tian, Shuyue Xing, Xingrui Li, Yangyang Luo et al.AAAI 2025 · 3 citations
- DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite AutomatonYiyou Sun, Junjie Hu, Wei Cheng, Haifeng ChenICML 2024 · 4 citations
- LiR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented GenerationGuo Chen, Junjie Huang, Huaijin Xie, Fei Sun et al.AAAI 2026
