REVIEW 40 cited by
Document Expansion by Query Prediction
Not yet reviewed by Pith; the record is open.
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
Signed reviews
read the original abstract
One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content.From the perspective of a question answering system, this might comprise questions the document can potentially answer. Following this observation, we propose a simple method that predicts which queries will be issued for a given document and then expands it with those predictions with a vanilla sequence-to-sequence model, trained using datasets consisting of pairs of query and relevant documents. By combining our method with a highly-effective re-ranking component, we achieve the state of the art in two retrieval tasks. In a latency-critical regime, retrieval results alone (without re-ranking) approach the effectiveness of more computationally expensive neural re-rankers but are much faster.
Forward citations
Cited by 40 Pith papers
-
KuaiSearch: An E-Commerce Search Dataset with Authentic Queries and Product Texts for Recall, Ranking, and Relevance
KuaiSearch is a new large-scale, plaintext e-commerce search dataset from Kuaishou spanning recall, ranking, and relevance tasks.
-
Skills Know Their Neighbors: Cluster-Contrastive Capability Pages for Skill Retrieval
Cluster-contrastive Capability Pages that add positive triggers, negative boundaries, and discriminative bodies to skill documents improve first-stage Recall@10 by 2.94 points on average and end-to-end task success by...
-
Bridging the Question-Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddings
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.
-
Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL Schema Retrieval
Schema retrieval can be benchmarked as retrieval, and corpus-adaptive fine-tuning lifts a 305M embedder to 75.6 recall@10, rivaling 4–8B models.
-
Retrieval-Oriented Code Representations in Agentic Bug Localization
Role-aware file summaries give the best cost-effectiveness for file-level bug localization, beating file paths by up to 40% Hit@5 at far smaller footprint than raw source.
-
RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
RICE-PO trains retrieval agents using retrieval scores of intermediate summaries as local rewards, gated by influence and residual-stability estimates, outperforming group-based RL baselines on BRIGHT and BEIR.
-
Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps
Transferring modern encoders to normalized (lowercased) vocabularies via geometric embedding initialization and activation calibration closes the performance gap in learned sparse retrieval, achieving 52.4 nDCG on BEIR.
-
Understanding the Influence of Synthetic Data for Text Embedders
Synthetic data for text embedders yields sparse, task-localized MTEB gains and cross-task trade-offs, not broad robust improvement.
-
Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings
A new MTEB state-of-the-art for text embeddings is reported by combining multi-granularity LLM-generated hard negatives with curriculum training and an anchor-token-aware pooling method.
-
InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking
InsertRank shows that injecting BM25 scores into listwise LLM reranking prompts improves retrieval effectiveness on BRIGHT and R2MED across multiple LLM families.
-
Bridging the Gap: From Ad-hoc to Proactive Search in Conversations
Conv2Query fine-tunes an LLM to convert conversational context into ad-hoc queries, enabling off-the-shelf retrievers to work effectively on proactive search in conversations.
-
On the Scaling of Robustness and Effectiveness in Dense Retrieval
Robustness in dense retrieval follows power-law scaling laws, but with different exponents than effectiveness, and an adaptive weighting method (Pareto training) can improve the joint tradeoff more efficiently than sc...
-
ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation
ERU-KG uses reference-trained SPLADE term importances plus neighbor-document noun phrases to generate present and absent keyphrases without keyphrase labels, and reports strong benchmark and retrieval results.
-
Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval
Dense retrieval embeddings can be decomposed into interpretable latent concepts that serve both as explanations and as efficient sparse indexing units for retrieval.
-
Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization
Using direct preference optimization with reranker or GPT-3.5 preferences to align synthetic query generation improves downstream dense retrieval effectiveness on MS MARCO and TREC-DL.
-
Towards A Generalist Code Embedding Model Based On Massive Data Synthesis
CodeR, a 1.5B code embedding model trained on 2.9M synthetic retrieval triples through a three-stage curriculum, reports average NDCG@10 of 81.77 on CoIR and 72.8 on CodeRAG, above every baseline it lists.
-
QUPID: Quantified Understanding for Enhanced Performance, Insights, and Decisions in Korean Search Engines
A fine-tuned ensemble of a generative small language model and an embedding model outperformed zero-shot LLMs on Korean search relevance labeling, with reported Cohen's kappa of 0.646 versus 0.387 and 60x lower latency.
-
Leveraging Decoder Architectures for Learned Sparse Retrieval
For learned sparse retrieval, an encoder-decoder model that copies input to the decoder and max-pools MLM logits over all positions outperforms encoder-only and decoder-only backbones on MS MARCO.
-
FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation
FinDER offers 5,703 expert-annotated ambiguous financial queries grounded in 10-K filings and shows current retrieval and generation models still struggle with them.
-
Exploring $\ell_0$ Sparsification for Inference-free Sparse Retrievers
ℓ0 Mask and ℓ0 Activation improve inference-free sparse retrieval to 50.43 average NDCG@10 on BEIR, up from 49.52 for the base model.
-
Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
A membership inference attack on RAG systems crafts natural yes/no questions from a target document to detect its presence in the datastore, achieving high AUC while evading guardrail detectors.
-
CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs
A citation-graph retrieval framework that entangles sparse and dense relevance signals in a GNN over paper chunks reports state-of-the-art Hit@1 and answer accuracy on two research QA benchmarks.
-
NExtLong: Toward Effective Long-Context Training without Long Documents
Interleaving hard negative distractors between chunks of short documents improves long-context language model performance on HELMET and RULER.
-
Ranking Narrative Query Graphs for Biomedical Document Retrieval (Technical Report)
An unsupervised graph-based ranking method, partial matching, and ontological expansion improve biomedical document retrieval precision for concept-centric queries, but not for generic ones.
-
Multilingual Semantic Retrieval for Apple Music Search
Curriculum-trained multilingual bi-encoder hybridized with lexical retrieval via quantile matching delivers large tail-query conversion gains and 86% fewer empty results on Apple Music with no head or storefront regressions.
-
Towards a Relevance Posterior in Neural Information Access
Fusing a cached query-independent document-quality prior with BM25 or re-rankers improves TREC DL nDCG, with largest gains for RankZephyr, under a prior–likelihood view of retrieval.
-
LLM-Based Re-Ranking for Real Estate Search
An LLM pointwise re-ranker using user profiles and candidate-set statistics improved ranking quality in a real-estate marketplace, with statistically significant production gains of +5.3% CTR and +4.8% scheduled visits.
-
AudioBoost: Increasing Audiobook Retrievability in Spotify Search with Synthetic Query Generation
LLM-generated synthetic queries, indexed in both autocomplete and document content, produced small but statistically significant gains in audiobook impressions, clicks, and exploratory searches in a production A/B test.
-
On the Merits of LLM-Based Corpus Enrichment
LLM-generated, query-biased documents added to a search corpus improve retrieval effectiveness, RAG answer accuracy, and answer attribution in proof-of-concept experiments that use oracle-selected source documents.
-
Can Generative LLMs Create Query Variants for Test Collections? An Exploratory Study
GPT-3.5 generated query variants from information-need descriptions that overlap substantially with human variants in retrieved relevant documents, up to 71.1% at pool depth 100.
-
State Space Models are Strong Text Rerankers
Mamba-1 and Mamba-2 rerankers match comparably sized transformers on ranking accuracy but are less efficient in training and inference, with Mamba-2 improving on both fronts.
-
Advanced System Integration: Analyzing OpenAPI Chunking for Retrieval-Augmented Generation
An empirical study showing that LLM-generated endpoint summaries and an agent that retrieves details on demand improve OpenAPI endpoint discovery in a RAG system, at the cost of lower recall.
-
Improving Scientific Document Retrieval with Academic Concept Index
Academic concept indexes that track which concepts remain uncovered make LLM-generated training queries and document snippets more effective for scientific retrieval.
-
QZhou-Embedding Technical Report
QZhou-Embedding reports state-of-the-art average scores on MTEB and CMTEB as of August 27, 2025, using a two-stage multi-task pipeline with LLM-based data synthesis.
-
Automating AI Failure Tracking: Semantic Association of Reports in AI Incident Database
Sentence-embedding retrieval ranks the correct AI Incident in the top three for about 98% of test reports when titles and descriptions are combined, but possible train/test leakage likely inflates that number.
-
FullRecall: A Semantic Search-Based Ranking Approach for Maximizing Recall in Patent Retrieval
A three-phase patent retrieval pipeline achieved 100% recall on five examiner-cited test queries, but the score is driven by post hoc cutoff choices and a candidate set that already contains the target patents.
-
Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion
Exp4Fuse improves sparse retrieval by fusing the ranked lists from the original query and an LLM-expanded query using a modified reciprocal rank fusion.
-
Question-to-Question Retrieval for Hallucination-Free Knowledge Access: An Approach for Wikipedia and Wikidata Question Answering
A question-to-question retrieval system that maps user queries to LLM-generated questions about Wikipedia passages and Wikidata triples, returning the linked source text without answer generation.
-
Evaluating Hybrid Retrieval Augmented Generation using Dynamic Test Sets: LiveRAG Challenge
A hybrid BM25-plus-dense RAG system finished 4th in faithfulness and 11th in correctness at LiveRAG 2025, and its analysis found vocabulary alignment between questions and documents to be the most important performanc...
-
A Survey on Retrieval And Structuring Augmented Generation with Large Language Models
The paper presents a comprehensive survey and taxonomy of RAS methods, covering retrieval, text structuring, and LLM integration.
Discussion (0). Continue with ORCID to comment.