REVIEW 17 cited by
Query Expansion by Prompting Large Language Models
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
read the original abstract
Query expansion is a widely used technique to improve the recall of search systems. In this paper, we propose an approach to query expansion that leverages the generative abilities of Large Language Models (LLMs). Unlike traditional query expansion approaches such as Pseudo-Relevance Feedback (PRF) that relies on retrieving a good set of pseudo-relevant documents to expand queries, we rely on the generative and creative abilities of an LLM and leverage the knowledge inherent in the model. We study a variety of different prompts, including zero-shot, few-shot and Chain-of-Thought (CoT). We find that CoT prompts are especially useful for query expansion as these prompts instruct the model to break queries down step-by-step and can provide a large number of terms related to the original query. Experimental results on MS-MARCO and BEIR demonstrate that query expansions generated by LLMs can be more powerful than traditional query expansion methods.
Forward citations
Cited by 17 Pith papers
-
SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads
A gated hybrid retrieval system shows rule-based keywords beat LLM queries for retargeting but lose for prospecting, and routing 10% of users to LLM semantic search raises ad conversions by 27.6%.
-
PCTD: Preference-Guided Counterfactual Task Decomposition for Agent Tool Retrieval
A counterfactual difference reward plus a preference reward reduces reward hacking in LLM task decomposition and improves tool retrieval, especially for unseen tools.
-
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.
-
Benchmarking Information Retrieval Models on Complex Retrieval Tasks
CRUMB is a new benchmark for complex, multi-aspect retrieval tasks on which state-of-the-art retrieval models score poorly, and query rewriting does not rescue the best models.
-
Upcycling Candidate Tokens of Large Language Models for Query Expansion
Using unselected top-k candidate tokens from a single LLM decoding pass as extra query terms improves retrieval over standard keyword expansion while using far fewer tokens than document-level methods.
-
Text-to-SQL for Enterprise Data Analytics
An enterprise Text-to-SQL chatbot augmented with a knowledge graph, context ranking, and query-fixing agents achieves 53% correct or nearly correct answers on LinkedIn's internal benchmark, with knowledge graph compon...
-
TongSearch-QR: Reinforced Query Reasoning for Retrieval
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.
-
Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval
A two-stage RAG training pipeline, MoL continual pre-training plus GRPO reinforcement learning with single-passage training and multi-passage inference, reports state-of-the-art retrieval recall on NFCORPUS and SCIFAC...
-
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.
-
Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations
Xinyu, an integrated generative AI search engine with query decomposition, multi-source retrieval, and rich answer presentation, outperforms eight existing technologies in human evaluations.
-
Hierarchical Reranking for Scalable Financial RAG System
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.
-
LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge
An ensemble of zero-shot LLMs with BM25 retrieval and semantic reranking ranked first in one BioASQ 13 yes/no batch, with longer contexts observed to hurt answer quality.
-
A Case Study of Balanced Query Recommendation on Wikipedia
BalancedQR, extended to handle multiple bias dimensions with a Pareto front, recommends less biased Wikipedia queries, and a GloVe-plus-LLM candidate generation method dominates alternatives.
-
A Multi-Task Evaluation of LLMs' Processing of Academic Text Input
The abstract reports Gemini underperforms on four academic text tasks, but the attached full text is an unrelated biomedical retrieval paper, leaving the claims unverifiable.
-
AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration
A no-code workflow builder with hidden multi-agent decomposition yields positive usability scores, but the study does not support the claim of significant improvement.
-
GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval
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.
-
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.
Discussion (0). Sign in to comment.