Pith. sign in

REVIEW 5 cited by

Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.04055 v1 pith:22XYNIO6 submitted 2024-01-08 cs.IR

Priyanka Mandikal , Raymond Mooney This is my paper
classification cs.IR
keywords retrievaldensemodelscientificdocumentdocumentsdomainenhance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Traditional information retrieval is based on sparse bag-of-words vector representations of documents and queries. More recent deep-learning approaches have used dense embeddings learned using a transformer-based large language model. We show that on a classic benchmark on scientific document retrieval in the medical domain of cystic fibrosis, that both of these models perform roughly equivalently. Notably, dense vectors from the state-of-the-art SPECTER2 model do not significantly enhance performance. However, a hybrid model that we propose combining these methods yields significantly better results, underscoring the merits of integrating classical and contemporary deep learning techniques in information retrieval in the domain of specialized scientific documents.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Rethinking RAG in Long Videos: What to Retrieve and How to Use It?

    cs.AI 2026-06 unverdicted novelty 6.0 of 10

    Introduces V-RAGBench benchmark and CARVE method that selects per-chunk retrieval configurations via parallel retrievers and adaptive reranking, outperforming eight VideoRAG baselines.

  2. DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    DocRetriever introduces a framework using layout-aware sparse embeddings for hybrid encoding without OCR and a generalizable reasoning-augmented reranker for few-shot settings, plus the MultiDocR benchmark for evaluation.

  3. Introducing the Swiss Food Knowledge Graph: AI for Context-Aware Nutrition Recommendation

    cs.AI 2025-07 conditional novelty 5.0 of 10

    The paper introduces SwissFKG, a knowledge graph integrating Swiss recipes, nutrients, allergens, and dietary guidelines, populated via an LLM pipeline and used for a Graph-RAG question answering demo.

  4. KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities

    cs.CL 2025-07 reject novelty 4.0 of 10

    K2RAG combines knowledge graph retrieval, hybrid dense/sparse search, summarization, and a quantized LLM to achieve slightly higher answer similarity (mean 0.57) than naive RAG baselines on MultiHopRAG with lower VRAM...

  5. Harnessing Collective Intelligence of LLMs for Robust Biomedical QA: A Multi-Model Approach

    cs.CL 2025-08 conditional novelty 3.0 of 10

    Combining 13 open-source LLMs by majority voting and answer union achieved top BioASQ 2025 rankings, but the reported best combinations are selected by exhaustive search and lack statistical validation.

Pith tools