Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation

Prakhar Bansal; Shivangi Agarwal

cs.CLApr 3, 2026

Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation

Authors: Prakhar Bansal, Shivangi Agarwal

Abstract

Large language models (LLMs) encode vast world knowledge in their parameters, yet they remain fundamentally limited by static knowledge, finite context windows, and weakly structured causal reasoning. This survey provides a unified account of augmentation strategies along a single axis: the degree of structured context supplied at inference time. We cover in-context learning and prompt engineering, Retrieval-Augmented Generation (RAG), GraphRAG, and CausalRAG. Beyond conceptual comparison, we provide a transparent literature-screening protocol, a claim-audit framework, and a structured cross-paper evidence synthesis that distinguishes higher-confidence findings from emerging results. The paper concludes with a deployment-oriented decision framework and concrete research priorities for trustworthy retrieval-augmented NLP.

Figures & tables

Gap	Prompting	RAG	GraphRAG	CausalRAG
Knowledge gap	$\circ$	Yes	Yes	Yes
Retrieval gap	No	$\circ$	Yes	Yes
Reasoning gap	No	No	$\circ$	Yes

Table 1: Three failure gaps in knowledge-intensive question answering and paradigm-level coverage (authors’ synthesis based on cited literature).

Paradigm	Source	Dataset	Systems compared	Metric (unit)	Reported values	Delta
Prompting (CoT)	Wei et al. (2022)	GSM8K	PaLM 540B: CoT vs standard prompting	Solve rate (%)	57.0 vs 18.0	+39.0 pts
RAG	Lewis et al. (2020)	Natural Questions (Open-domain QA)	RAG vs T5-11B (closed-book)	Exact Match (EM, %)	44.5 vs 34.5	+10.0 pts
GraphRAG-Global (slice comparison)	Wang et al. (2025)	OpenAlex single-paper case study	GraphRAG-Global: abstract vs full text	Composite score (author-defined)	49.98 vs 76.37	+26.39
GraphRAG-Local (slice comparison)	Wang et al. (2025)	OpenAlex single-paper case study	GraphRAG-Local: abstract vs full text	Composite score (author-defined)	62.29 vs 84.27	+21.98
CausalRAG (slice comparison)	Wang et al. (2025)	OpenAlex single-paper case study	CausalRAG: abstract, intro, and full text	Composite score (author-defined)	72.43, 74.86, 91.69	+19.26 (abstract to full)
CausalRAG (k=s sweep)	Wang et al. (2025)	OpenAlex	CausalRAG: k=s=1 vs k=s=5	Author-reported score	0.534 vs 0.824	+0.290

Table 2: Quantitative evidence matrix with explicit metric definitions and scope constraints. All values are reported in the cited source studies.

Criterion	Prompting	RAG	GraphRAG	CausalRAG
Indexing cost	None	Low to Medium	High	High to Very High
Relational reasoning	Limited	Limited	Strong	Strong
Causal reasoning	Weak	Weak	Partial	Strong
Global summary	Weak	Moderate	Strong	Strong
Typical faithfulness	Low to Medium	Medium	Medium to High	High

Table 3: Comparative summary across paradigms (authors’ synthesis).

Claim	Primary support	Confidence	Notes
RAG improves factual grounding versus prompting-only baselines in knowledge-intensive QA.	Lewis et al. (2020) ; Chen et al. (2023)	High	Established across multiple benchmarks.
CausalRAG improves faithfulness and causal coherence over vanilla RAG and associative graph retrieval in reported settings.	Wang et al. (2025) ; Samarajeewa et al. (2024)	Medium	Evidence is promising but still limited in scale.
GraphRAG supports stronger relational and global-corpus reasoning than flat top- $k$ chunk retrieval.	Edge et al. (2024) ; Han et al. (2025) ; Peng et al. (2024)	Medium to High	Strong conceptual fit; evaluation setups vary.
Long-context prompting alone suffers from placement sensitivity (lost-in-the-middle).	Liu et al. (2024)	High	Strong evidence in controlled long-context evaluations.
Automated causal extraction remains error-prone and expensive in current LLM pipelines.	Jiralerspong et al. (2024) ; Wang et al. (2025)	Medium	Active research area; methods evolving quickly.

Table 4: Claim audit for key statements in this survey (authors’ evidence grading with explicit source attribution).

Knowledge Augmentation for Language Models

Knowledge augmentation for language models adds external or newly learned information to improve factuality, reasoning, and domain performance.

See all 167 papers

When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation
Aug 17, 2026Haolin Jin, Pengyue Yang, Huaming ChenRAG Citation Faithfulness Retrieval-Augmented Generation
School of Electrical and Computer Engineering The University of Sydney Sydney, NSW, Australia
Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG
Sep 17, 2025Harshad Khadilkar, Abhay GuptaRetrieval-Augmented Generation Graph Retrieval-Augmented Generation
Indian Institute of Technology Bombay · Indian Institute of Technology Patna
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
Apr 9, 2026Zhengyi Zhao, Shubo Zhang, Zezhong Wang +7Hallucination in RAG Retrieval-Augmented Generation
The Chinese University of Hong Kong · Ministry of Education Key Laboratory of High Confidence Software Technologies, CUHK · University of International Relations +2

Aug 17, 2026J/K move · Enter open · S save

When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation

Haolin Jin, Pengyue Yang, Huaming Chen

School of Electrical and Computer Engineering The University of Sydney Sydney, NSW, Australia

RAG Citation Faithfulness Retrieval-Augmented Generation RAG Robustness Knowledge Conflicts in Language Models

Open paper AskPDF arXiv

Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trust problem: retrieved context may be useful, irrelevant, or even misleading. Existing RAG systems often apply a fixed trust policy toward retrieved evidence, which can either over-trust incorrect context or underuse context when the user explicitly asks for context-following behavior. Therefore, we propose Intent-Guided Decoding (IGD), a framework that arbitrates between retrieved context and parametric memory according to user intent. IGD uses answer-level filtering and token-level correction to steer the final decoding trajectory between retrieved context and parametric memory. We evaluate IGD on three faithful QA benchmarks and three factual-conflict benchmarks across five LLMs, IGD substantially improves factual recovery, achieving gains of up to 65.4 percentage points on factual-conflict benchmarks over Direct RAG, while preserving or improving strict context-following behavior, this findings highlight the importance of balancing factuality and faithfulness in RAG.

Abstract

Knowledge Augmentation for Language Models

Explore similar work

When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation

Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG

Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation