Pith. sign in

REVIEW 20 cited by

Precise Zero-Shot Dense Retrieval without Relevance Labels

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 2212.10496 v1 pith:WBQYXAMU submitted 2022-12-20 cs.IR cs.CL

Luyu Gao , Xueguang Ma , Jimmy Lin , Jamie Callan This is my paper · ORCID
classification cs.IRcs.CL
keywords densedocumentrelevancezero-shothyderetrievalvectoracross
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the difficulty of zero-shot learning and encoding relevance. Instead, we propose to pivot through Hypothetical Document Embeddings~(HyDE). Given a query, HyDE first zero-shot instructs an instruction-following language model (e.g. InstructGPT) to generate a hypothetical document. The document captures relevance patterns but is unreal and may contain false details. Then, an unsupervised contrastively learned encoder~(e.g. Contriever) encodes the document into an embedding vector. This vector identifies a neighborhood in the corpus embedding space, where similar real documents are retrieved based on vector similarity. This second step ground the generated document to the actual corpus, with the encoder's dense bottleneck filtering out the incorrect details. Our experiments show that HyDE significantly outperforms the state-of-the-art unsupervised dense retriever Contriever and shows strong performance comparable to fine-tuned retrievers, across various tasks (e.g. web search, QA, fact verification) and languages~(e.g. sw, ko, ja).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 20 Pith papers

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

  1. RAG-Stack: Co-Optimizing RAG Serving Performance and Quality

    cs.DB 2026-08 conditional novelty 7.0 of 10

    RAG-Stack jointly optimizes RAG algorithm choices and serving-system settings via sub-metric-aware multi-objective Bayesian optimization plus an analytical performance model, reporting Pareto frontiers covering 52.5% ...

  2. Bridging the Question-Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddings

    cs.IR 2026-07 conditional novelty 6.0 of 10

    Precomputing hypothetical question embeddings for each text chunk at indexing time shifts retrieval to question–question matching and improves context precision and claim recall in RAG.

  3. Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees

    cs.LG 2026-07 conditional novelty 6.0 of 10

    C3R certifies per-domain retrieval contamination budgets using a two-split conformal scheme, without query-time domain labels.

  4. FitText: Evolving Agent Tool Ecologies via Memetic Retrieval

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    FitText embeds memetic evolutionary retrieval inside the agent's reasoning loop to iteratively refine pseudo-tool descriptions, raising retrieval rank from 8.81 to 2.78 on ToolRet and pass rate to 0.73 on StableToolBench.

  5. BEAR: Budgeted Evidence Allocation for Multi-Document Reasoning

    cs.CL 2026-01 conditional novelty 6.0 of 10

    A budget-controlled two-path hierarchical retrieval method reports near-full-context accuracy on multi-hop QA with up to 94% token savings, but the reported numbers are internally inconsistent and no artifacts are released.

  6. HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Serving

    cs.DB 2025-07 conditional novelty 6.0 of 10

    HedraRAG uses a graph abstraction and dynamic transformations to pipeline generation and retrieval stages, achieving 1.5x to 5x speedups in heterogeneous RAG serving.

  7. Maximally-Informative Retrieval for State Space Model Generation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    RICO ranks documents by how much they reduce an SSM's question perplexity, using gradient-document inner products, and matches BM25 while often beating E5 on answer quality without finetuning.

  8. TongSearch-QR: Reinforced Query Reasoning for Retrieval

    cs.IR 2025-06 conditional novelty 6.0 of 10

    TongSearch-QR trains 1.5B and 7B models with GRPO and a frozen-embedding reward to rewrite queries, reaching 27.9 nDCG@10 on BRIGHT with BM25, above GPT-4o's 26.5.

  9. Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queries

    cs.IR 2025-05 conditional novelty 6.0 of 10

    NS-IR translates queries and documents into first-order logic, then uses logic alignment and a connective constraint to rerank dense retrieval results, improving zero-shot retrieval especially on negative-constraint queries.

  10. Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style

    cs.AI 2025-05 conditional novelty 6.0 of 10

    A genetic algorithm evolves an LLM teacher's lecture style in a simulated classroom, and a new personalized RAG method helps LLM students retrieve notes, improving simulated scores and human ratings of lecture quality.

  11. SlimRAG: Retrieval without Graphs via Entity-Aware Context Selection

    cs.IR 2025-06 conditional novelty 5.0 of 10

    SlimRAG shows that an entity-aware inverted index without graphs can match or beat graph-based RAG retrieval on HotpotQA while using far fewer index tokens.

  12. Hierarchical Reranking for Scalable Financial RAG System

    cs.IR 2026-07 reject novelty 4.0 of 10

    A finance-specific RAG pipeline combining table-to-JSON conversion, two-stage reranking, and long-context split-fusion reports NDCG@20=0.7918 and second place in the ICAIF '24 FinanceRAG challenge.

  13. Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data

    cs.CL 2025-07 reject novelty 4.0 of 10

    An enterprise RAG framework combining hybrid retrieval, cross-encoder reranking, and structure-aware table indexing claims relative gains of 15% in Precision@5, 13% in Recall@5, and 16% in MRR over a dense-only baseline.

  14. Question Decomposition for Retrieval-Augmented Generation

    cs.CL 2025-07 conditional novelty 4.0 of 10

    Splitting multi-hop questions into subquestions and reranking the merged retrieval pool improves RAG evidence coverage and answer accuracy on MultiHop-RAG and HotpotQA.

  15. DoTA-RAG: Dynamic of Thought Aggregation RAG

    cs.CL 2025-06 conditional novelty 4.0 of 10

    DoTA-RAG combines query rewriting, namespace routing, dense retrieval, BM25 pruning, and reranking to answer questions over a 15M-document corpus, with reported correctness gains but fragile faithfulness under output caps.

  16. GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval

    cs.IR 2025-06 conditional novelty 4.0 of 10

    GOLFer filters hallucinated sentences from small-LM-generated hypothetical documents and reweights the rest into the query, improving retrieval at lower cost than large LLM expansion.

  17. Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion

    cs.IR 2025-06 conditional novelty 4.0 of 10

    Exp4Fuse improves sparse retrieval by fusing the ranked lists from the original query and an LLM-expanded query using a modified reciprocal rank fusion.

  18. Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models

    cs.IR 2025-05 reject novelty 4.0 of 10

    In tri-modal hybrid retrieval with GPT-4o reranking, MiniLM-v6 matches or beats BGE-Large on SciFact, FIQA, and NFCorpus despite being far smaller.

  19. Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarization

    cs.CL 2025-05 conditional novelty 4.0 of 10

    XSum, a question-generation plus editor RAG pipeline, produces survey-style summaries from multiple scientific papers and reports improved scores on the SurveySum benchmark.

  20. Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks

    cs.CL 2025-05 reject novelty 3.0 of 10

    Fine-tuning Llama-3-8b and Mistral-7b-v0.3 on LLM-generated QA pairs from IBM Technotes can improve no-context QA scores over training on human-annotated TechQA data, but the evaluation may be inflated by test-documen...

Pith tools