# CoCR-RAG: Enhancing Retrieval-Augmented Generation in Web Q&A via Concept-oriented Context Reconstruction

arXiv: https://arxiv.org/abs/2603.23989 · HTML: https://mlsanity.com/paper/2603.23989/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 25 of 25)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [Simple Entity-Centric Questions Challenge Dense Retrievers](https://mlsanity.com/paper/2109.08535/) (2021)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2402.18154/) (2024)
- [Planning with Learned Entity Prompts for Abstractive Summarization](https://mlsanity.com/paper/2104.07606/) (2021)
- [Learning to Compress Prompt in Natural Language Formats](https://mlsanity.com/paper/2402.18700/) (2024)
- [Semantic Neural Machine Translation using AMR](https://mlsanity.com/paper/1902.07282/) (2019)
- [Incomplete Utterance Rewriting as Semantic Segmentation](https://mlsanity.com/paper/2009.13166/) (2020)
- [Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation](https://mlsanity.com/paper/2403.14952/) (2024)
- [Analyzing and Learning from User Interactions for Search Clarification](https://mlsanity.com/paper/2006.00166/) (2020)
- [HighRES: Highlight-based Reference-less Evaluation of Summarization](https://mlsanity.com/paper/1906.01361/) (2019)
- [AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model](https://mlsanity.com/paper/2305.16734/) (2023)
- [A Tree-based Decoder for Neural Machine Translation](https://mlsanity.com/paper/1808.09374/) (2018)
- [An AMR Aligner Tuned by Transition-based Parser](https://mlsanity.com/paper/1810.03541/) (2018)
- [Explicit Syntactic Guidance for Neural Text Generation](https://mlsanity.com/paper/2306.11485/) (2023)
- [Retrieval-Augmented Dialogue Knowledge Aggregation for Expressive Conversational Speech Synthesis](https://mlsanity.com/paper/2501.06467/) (2025)
- [Concept than Document: Context Compression via AMR-based Conceptual Entropy](https://mlsanity.com/paper/2511.18832/) (2025)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) has shown promising results in enhancing Q&A by incorporating information from the web and other external sources. However, the supporting documents retrieved from the heterogeneous web often originate from multiple sources with diverse writing styles, varying formats, and inconsistent granularity. Fusing such multi-source documents into a coherent and knowledge-intensive context remains a significant challenge, as the presence of irrelevant and redundant information can compromise the factual consistency of the inferred answers. This paper proposes the Concept-oriented Context Reconstruction RAG (CoCR-RAG), a framework that addresses the multi-source information fusion problem in RAG through linguistically grounded concept-level integration. Specifically, we introduce a concept distillation algorithm that extracts essential concepts from Abstract Meaning Representation (AMR), a stable semantic representation that structures the meaning of texts as logical graphs. The distilled concepts from multiple retrieved documents are then fused and reconstructed into a unified, information-intensive context by Large Language Models, which supplement only the necessary sentence elements to highlight the core knowledge. Experiments on the PopQA and EntityQuestions datasets demonstrate that CoCR-RAG significantly outperforms existing context-reconstruction methods across these Web Q&A benchmarks. Furthermore, CoCR-RAG shows robustness across various backbone LLMs, establishing itself as a flexible, plug-and-play component adaptable to different RAG frameworks.