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

Kaize Shi; Xueyao Sun; Qika Lin; Firoj Alam; Qing Li; Xiaohui Tao; Guandong Xu

cs.CLMar 25, 2026

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

Authors: Kaize Shi, Xueyao Sun, Qika Lin, Firoj Alam, Qing Li, Xiaohui Tao, Guandong Xu

Organizations: University of Southern Queensland, QLD, Australia · University of Technology Sydney, NSW, Australia · The Hong Kong Polytechnic University, Hong Kong, China · National University of Singapore, Singapore, Singapore ·

Abstract

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.

Figures & tables

Figure 1: Example of RAG based on the concept-oriented reconstructed context.

Figure 2: The overview of the Concept-oriented Context Reconstruction RAG framework, which consists of three components: (a) information retrieval , (b) context reconstruction , and (c) reconstructed context-based inference . The different arrow colors indicate the corresponding components.

Figure 3: The evaluation results depict trends in $Acc.\uparrow$ and $AUC\uparrow$ on the PopQA dataset. The vertical axis denotes $Acc$ , while the horizontal axis represents the number of supporting documents, $K$ . The polyline illustrates the fluctuation in $Acc$ with varying $K$ . The shaded area represents $AUC$

Figure 4: The evaluation results illustrate trends in $Acc.\uparrow$ and $AUC\uparrow$ on the EntityQuestion dataset, following the same axis and symbol definitions as in Fig. 3 .

$\mathcal{D}$	G-1.3	G-2.7	G-j-6	O-1.3	O-2.7	O-6.7	b-560	b-1b1	b-1b7	b-3	L-7	L-13	$\sigma$
Vanilla	539.91	555.70	490.49	569.08	583.23	548.19	501.18	560.34	556.89	565.54	515.85	554.59	27
Keywords	363.29	405.28	215.69	456.49	438.54	440.44	341.82	453.85	461.18	455.32	507.55	533.24	81
Summary	401.59	430.34	295.96	486.48	453.17	338.15	439.64	464.63	478.31	462.03	404.63	438.62	55
SelCon	376.17	447.93	400.95	511.20	465.31	539.90	297.28	491.25	465.67	504.65	579.12	586.74	80
LLMLingua	565.77	562.33	500.55	583.85	587.63	559.34	503.56	568.57	555.43	551.21	585.21	585.25	28
CoCR-RAG	567.45	574.05	514.95	587.84	602.97	584.28	524.32	576.56	572.85	582.81	594.88	595.84	26

Table 2: The quantitative results of

AUC\uparrow

for the PopQA dataset, with the full name order of the LLMs as follows: GPT-Neo-1.3B, GPT-Neo-2.7B, GPT-j-6b, OPT-1.3b, OPT-2.7b, OPT-6.7b, bloom-560m, bloom-1b1, bloom-1b7, bloom-3b, LLaMA-2-chat-7b, LLaMA-2-chat-13b. The best results are in bold , and the next best results are in underlined . The increased

\Delta

has been marked.

$\mathcal{D}$	G-1.3	G-2.7	G-j-6	O-1.3	O-2.7	O-6.7	b-560	b-1b1	b-1b7	b-3	L-7	L-13	$\sigma$
Vanilla	419.76	477.67	444.72	469.79	502.47	481.28	395.26	473.16	477.78	486.80	454.46	488.31	30
Keywords	223.65	286.79	147.71	316.44	339.38	333.05	238.12	329.76	366.60	360.61	445.11	444.69	83
Summary	283.05	310.28	192.44	389.03	348.75	250.26	302.53	321.16	390.52	335.85	327.42	329.31	53
SelCon	234.72	314.73	303.06	366.26	366.92	460.20	179.64	359.63	344.78	421.39	487.63	499.92	93
LLMLingua	432.41	465.59	453.87	483.31	518.63	522.23	396.49	467.85	480.73	476.79	505.94	523.09	36
CoCR-RAG	470.74	492.66	463.07	501.31	535.93	523.77	422.84	494.17	503.37	512.23	526.92	538.31	32

Table 3: The quantitative results of

AUC\uparrow

for the EntityQuestions dataset follow the LLMs’ order and symbol definitions as presented in Table 2 .

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Figure A1: The node order traversed by DFS( $\cdot$ ) in the AMR graph, where the nodes marked here are not the final distilled concepts.

Supporting Document: Houston Dynamo are an American professional soccer club based in Houston, Texas. The franchise competes in Major League Soccer (MLS), as a member of the Western Conference.

(m / multi-sentence

:snt1 (c / club

:mod (s / soccer)

:mod (p / professional)

:mod (c2 / country

:wiki "United_States"

Appendix

Table A1: An example of the parsed AMR graph. Nodes containing concepts are highlighted , including "club, soccer, professional, American, based, Texas, Houston Dynamo. competes, franchise, Major League Soccer, Western Conference, member".

Panel of Table 9 — Table A2: Accuracy ( $Acc\uparrow$ ) on the PopQA dataset. The best results for each LLM with setting $K$ are in bold , and the next best results are in underlined . $\Delta$ here represents the difference between the CoCR-RAG and Vanilla, and the increased and decreased $\Delta$ are marked differently. The best results for each of $K$ are marked .

Panel of Table 10 — Table A3: Accuracy ( $Acc\uparrow$ ) the EntityQuestions dataset. The definitions of symbols are the same with the Table A2 .

Retrieval-Augmented Generation

Retrieval-augmented generation connects language models to external knowledge so answers can use current, domain-specific evidence.

See all 792 papers

Apr 17, 2026

CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents

Retrieval-Augmented Generation (RAG) systems lose retrieval accuracy when similar documents coexist in the vector database, causing unnecessary information, hallucinations, and factual errors. To alleviate this issue, we propose CHOP, a framework that iteratively evaluates chunk relevance with Large Language Models (LLMs) and progressively reconstructs documents by determining their association with specific topics or query types. CHOP integrates two key components: the CNM-Extractor, which generates compact per-chunk signatures capturing categories, key nouns, and model names, and the Continuity Decision Module, which preserves contextual coherence by deciding whether consecutive chunks belong to the same document flow. By prefixing each chunk with context-aware metadata, CHOP reduces semantic conflicts among similar documents and enhances retriever discrimination. Experiments on benchmark datasets show that CHOP alleviates retrieval confusion and provides a scalable approach for building high-quality knowledge bases, achieving a Top-1 Hit Rate of 90.77% and notable gains in ranking quality metrics.

Hyunseok Park, Jihyeon Kim, Jongeun Kim +1

HDC LABS Republic of Korea

Document Chunking Retrieval-Augmented Generation

Ask PDF

Feb 1, 2024

HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA

Retrieval-augmented generation (RAG) has rapidly advanced the language model field, particularly in question-answering (QA) systems. By integrating external documents during the response generation phase, RAG significantly enhances the accuracy and reliability of language models. This method elevates the quality of responses and reduces the frequency of hallucinations, where the model generates incorrect or misleading information. However, these methods exhibit limited retrieval accuracy when faced with numerous indistinguishable documents, presenting notable challenges in their practical application. In response to these emerging challenges, we present HiQA, an advanced multi-document question-answering (MDQA) framework that integrates cascading metadata into content and a multi-route retrieval mechanism. We also release a benchmark called MasQA to evaluate and research in MDQA. Finally, HiQA demonstrates the state-of-the-art performance in multi-document environments.

Xinyue Chen, Pengyu Gao, Jiangjiang Song +1

1Nanjing University of Aeronautics and Astronautics. · 2Southeast University, Nanjing, Jiangsu, China.

Retrieval-Augmented Generation Multi-Document QA Document QA Information Retrieval RAG Evaluation

Ask PDF

Oct 21, 2026

Graph Topology Meets Energy-Driven Pathfinding: Preserving Contextual Consistency in Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) frequently integrates knowledge graphs (KGs) for complex multi-hop question answering. However, their performance is increasingly bottlenecked by the knowledge structuring and reasoning processes. (i) Severe semantic loss: Distilling continuous texts into discrete symbols strips away contextual nuances and narrative coherence. (ii) Pronounced modality mismatch: Fragmented graph structures clash with the continuous texts LLMs are pre-trained on, while rewriting them into natural language introduces generative noise and omits information. To address these limitations, we propose ThreadRAG, a semantic-topology-based RAG framework for context-preserving knowledge structuring and modality-native evidence reasoning. ThreadRAG introduces a Semantic Topology Mapper (STM), which organizes retrieved documents into context-intact Semantic Nodes and constructs a Semantic Topology Graph (STG) through narrative, semantic, and lexical edges. It further incorporates Energy-Driven Pathfinding (EDP), which identifies query-relevant subgraphs via energy diffusion and deterministically linearizes them into coherent textual evidence paths. Experiments on three multi-hop QA benchmarks demonstrate that ThreadRAG consistently outperforms strong baselines. Notably, it achieves a 14.4% EM improvement over text-centric methods on HotpotQA and surpasses the best baseline by 5.8% EM on 2WikiMultihop, while reducing token cost to 23.3% of the strongest baseline.

Yufeng Li, Zaijing Li, Fuchen Zhang +3

Central South University, Changsha, China · Harbin Institute of Technology, Shenzhen, China

Graph Retrieval-Augmented Generation Retrieval-Augmented Reasoning Multi-Hop QA KG Construction

Ask PDF

Abstract

Retrieval-Augmented Generation

Explore similar work

CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents

HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA

Graph Topology Meets Energy-Driven Pathfinding: Preserving Contextual Consistency in Retrieval-Augmented Generation