Jul 2026· NLP & Big Data· pp. 79-98· 0 citations· 33 references
TL;DR
The Adaptive Multi-Stage Vector Retrieval (AMSVR) framework is proposed, prioritising weighted, drift-resistant composition over uniform fusion, and offers tailored configurations: AMSVR-Scientific (dense + tuned hybrid) peaks at NDCG@10 = 0.7570 on SciFact, while AMSVR-Full (seven stages) targets broader, noisier corpora where Recall@100 matters most.
Abstract
Retrieval-Augmented Generation (RAG) is the standard for grounding Large Language Models (LLMs), but its parts' embeddings, lexical scoring, query expansion, reranking, and adaptive sizing do not always compose additively. Under default configurations, adding naïve hybrid retrieval with Reciprocal Rank Fusion degrades NDCG@10 by up to 5.6% on scientific corpora; temperature-sampled query expansion with a small LLM further degrades it by 16.8%. To address this, we propose the Adaptive Multi-Stage Vector Retrieval (AMSVR) framework, prioritising weighted, drift-resistant composition over uniform fusion. Rather than a one-sizefits-all system, AMSVR offers tailored configurations: AMSVR-Scientific (dense + tuned hybrid) peaks at NDCG@10 = 0.7570 on SciFact, while AMSVR-Full (seven stages) targets broader, noisier corpora where Recall@100 matters most. We evaluate on three BEIR benchmarks (SciFact, NFCorpus, FIQA), release an offline configuration-diagnostic tool, and provide a per-corpus recipe for selecting which stages to enable.
Retrieval-augmented generation (RAG) systems depend on retrieval modules to supply grounding evidence for large language models. While hybrid approaches combining sparse and dense retrievers improve performance, most rely on fixed weights that ignore query-specific and corpus-specific variation. Similarly, query expansion has long been used to enrich recall, but its integration with original queries is usually static and can introduce noise. We present Q U DAR, a dual-perspective adaptive retrieval framework motivated by a systematic analysis of retrieval behavior across retriever type (sparse vs. dense) and query format (original vs. expanded). Leveraging margin-derived confidence (e.g., top-1–top-2 score gaps) and LLM-based relevance scoring, Q U DAR dynamically assigns query-specific weights, enabling effective integration of complementary retrieval signals while mitigating noise. Q U DAR is lightweight, retriever-agnostic, and broadly applicable. Experiments show consistent gains over static baselines, improving retrieval quality by 12 – 16 % and yielding more stable performance across queries.
Joeun Kim, Seunghyouk Yoon, Xuan-Bach Le et al.· Annual Meeting of the Associ...· 1 citation
Retrieval-Augmented Generation (RAG) effectively mitigates the knowledge cutoff and hallucination issues of large language models by incorporating external knowledge bases. However, standard RAG applies a uniform retrieval strategy to all question types and feeds redundant retrieval results directly into the generator, leading to high token consumption and potentially degraded answer quality. This paper proposes SAC-RAG (Semantic Adaptive Compress RAG), a unified framework that integrates question-type-adaptive retrieval with context compression. SAC-RAG first classifies queries into three types—factual, definitional, and reasoning—via an LLM classifier, applies a differentiated retrieval strategy for each type, then uses a unified LLM context compression module to extract evidence snippets, and finally generates answers from the compressed and refined context. To independently quantify the contribution of each component, we design four progressive ablation experiments on three multi-hop QA datasets—HotpotQA, 2WikiMultiHopQA, and MuSiQue—and evaluate using four metrics: Exact Match, F1, Recall@10, and token consumption. Experimental results show that SAC-RAG reduces token consumption by 38%–58% at the cost of only a 1–2 percentage point EM drop, with EM actually improving after compression for reasoning-type questions, achieving the optimal quality–efficiency trade-off in terms of token consumption, with a moderate increase in per-query latency due to additional LLM calls. SAC-RAG offers a modular and interpretable optimization solution for the efficient deployment of RAG in real-world settings.
Deyu Zhang, Hongqiang Yu, Jinze Huo et al.· IEEE Access· 0 citations
Large language models may suffer from insufficient context use and unsupported generation in question answering tasks that require external knowledge. This study compares the main strategies affecting retrieval and generation performance in retrieval-augmented generation systems within a common experimental setting. In addition to a standard dense retrieval baseline, we evaluate multi-query, hypothetical document, hypothetical question, sparse-dense hybrid retrieval, and chunk compression, and we also propose an integrated method (FUSERAG) that combines these components. Experiments are conducted on a dataset containing 223 documents, 7933 chunks, and 1488 question-answer instances. Results show that the proposed method achieves the highest Mean Reciprocal Rank, nDCG at 5, and recall at 5 at the retrieval level, while the sparse-dense hybrid approach yields the best generation results.
Buğra Şimşek, Korhan Sevinç, Helen Parlar et al.· Signal Processing and Commun...· 0 citations
We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19. Rather than proposing a new model, we evaluate a fixed scientific RAG pipeline across three corpus scales: 1,034 chunks (1K papers), 5,160 chunks (5K papers), and 15,480 chunks (15K papers). The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation. Across these settings, hybrid retrieval is more robust than either sparse-only or dense-only retrieval in our setting, reaching Recall@10 of 1.000 at 1K and 15K. In contrast, an MS MARCO-trained cross-encoder reranker reduces precision on the scientific corpus, suggesting that domain mismatch can outweigh the benefits of stronger query-passage interaction. Generation faithfulness measured with RAGAS increases with corpus scale in our setup. Retrieval evaluation uses pseudo-relevance labels derived from the hybrid system, so we treat the results as controlled comparative evidence rather than a benchmark claim. We release code, indexes, and evaluation outputs to support replication and follow-up studies.
Kaysarul Anas Apurba, Mahade Hasan, Rofiqul Alam Shehab et al.· 0 citations
Building question-answering systems that can read a document and answer naturally phrased questions about it is difficult when retrieval is left to either keyword matching or dense vector search alone, since each method has blind spots that surface as missed context, near-miss answers, or content invented by the underlying language model. This paper describes an optimized hybrid Retrieval-Augmented Generation (RAG) pipeline built to reduce these failure modes by combining two complementary retrieval signals: dense semantic similarity computed over a FAISS vector index, and sparse lexical scoring computed with BM25. Candidates returned by both retrievers are merged and passed through a Cross-Encoder re-ranking stage that scores each query-passage pair jointly, pushing the most contextually relevant chunks to the top before they reach the language model. Final answers are produced by Google’s Gemini model under a prompt that restricts it to the supplied context, which keeps the output tied to the source document rather than to whatever the model already “knows.” The pipeline is exposed through a Streamlit application that lets a user upload a PDF and ask questions about it in plain language, returning each answer alongside a confidence estimate and the page it came from. Evaluation on a multi-page technical PDF document shows that the hybrid retrieval and re-ranking stages together raise retrieval precision and reduce irrelevant or unsupported answers compared with retrieval limited to a single method, supporting the use of this approach for reliable, document-grounded question answering.
Vishwa K Dave, Pallavi· International Research Journ...· 0 citations
Retrieval-Augmented Generation (RAG), which combines text generation and document retrieval, is one of the more useful methods for maintaining big language model outputs based on actual, verifiable sources rather than the model's own stored knowledge. However, what is initially extracted from the retrieval stage has a significant impact on how well a RAG system responds to a query. Using the Stanford Question Answering Dataset (SQuAD) as the testbed, this study especially examines how the similarity threshold employed during dense retrieval affects both retrieval quality and, later on in the pipeline, the quality of the final answer. The multi-qa-mpnet-base-dot-v1 embedding model was used to encapsulate context passages and questions, which were then compared using cosine similarity. The answer generator was LLaMA 3.1 8B, which was accessed using the Groq API. Fifty questions selected from the SQuAD validation set were used to test eleven threshold values, ranging from 0.0 to 1.0 in steps of 0.1. The quality of retrieval was evaluated by the measures Recall, Precision, and Mean Reciprocal Rank (MRR). The generated answers were assessed by means of Exact Match (EM) and F1 Measure. The baseline performance (at 0.0 threshold) had F1 at 0.827 and EM at 0.72, while for the 0.3 threshold it became F1 at 0.848 and EM at 0.78. Once past the 0.5 threshold, all metrics showed a sharp drop. Overall, the conclusions that can be drawn from this experiment are that threshold-based filtering of context significantly improves the performance of a RAG model.
Yehezkiel Fienathan Bolo Dadi, Cendra Putra· Journal of Artificial Intel...· 0 citations