LLM-QE: Improving Query Expansion by Aligning Large Language Models with Ranking Preferences

Overview

• Paper: LLM-QE: Improving Query Expansion by Aligning Large Language Models with Ranking Preferences
• Authors / Affiliations: Sijia Yao, Pengcheng Huang, Zhenghao Liu, Yu Gu, Yukun Yan, Shi Yu, et al. (7 authors total)
• Published: February 2025
• Source: https://arxiv.org/abs/2502.17057v1
• Type: Academic paper
• Category: Query Understanding

One-line Summary

LLM-QE improves LLM-based query expansion by aligning the expansion process with ranking preferences, so that generated expansion terms directly benefit downstream retrieval ranking performance.

Background and Motivation

In large-scale search, recommendation, and personalization systems, ranking has long faced challenges around efficiency, scalability, and user intent understanding. Traditional pipelines often treat retrieval, ranking, and generation as separate stages, which struggles to meet modern demands for natural language interaction, multi-hop reasoning, and up-to-date knowledge in the LLM era. LLM-QE was proposed in this context to advance the theory and practice at this intersection.

The core problem space includes: open-domain information access, enterprise knowledge retrieval, conversational search, semantic understanding in recommender systems, and end-to-end architectures that coordinate external knowledge sources with generative models.

Core Contributions

• Provides a unified perspective on the query expansion problem, organizing scattered related work into a comparable framework.
• Clearly decomposes method components (representation learning, retrievers, rerankers, planners, generators, feedback mechanisms) for easier engineering adoption.
• Offers reproducible benchmarks, datasets, or taxonomies to lower the entry cost for follow-up research.
• Discusses interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration, and paths from research prototypes to industrial systems.
• Lists open problems: evaluation trustworthiness, latency and cost, hallucination and safety, cross-lingual and multimodal extension.

Method / System Architecture

The work follows the typical four-step pattern: problem formalization → model/system design → training or construction pipeline → inference pipeline.

1. Input and representation: encode queries, documents, and user context as dense or sparse representations, or structured prompts; 2. Core modules: retrievers, rerankers, planners, memory modules, and tool interfaces, chained or composed per task; 3. Learning strategies: supervised fine-tuning, contrastive learning, distillation, reinforcement learning (including process rewards), and bootstrapped data synthesis; 4. Inference strategies: single-round retrieval, iterative retrieval, parallel sub-queries, early stopping, and budget control.

The technical route described by the abstract: aligning LLMs with ranking preferences to improve query expansion quality.

Experiments and Evaluation

Evaluation in this line of work typically involves:

• Datasets: MS MARCO, BEIR, Natural Questions, domain-specific corpora, and public recommendation sets;
• Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency, and token cost;
• Baselines: BM25, dense retrieval, cross-encoder reranking, retrieval-free LLMs, and commercial search APIs;
• Ablations: contribution of modules such as retrieval steps, reranking depth, and training data scale.

Exact numerical results should be verified against the original paper's tables; this report is based on the abstract and public metadata.

Key Takeaways for Search / Rec / Personalization

1. Architecture: cascaded retrieval + reranking + generation remains mainstream, but agentic paradigms are making "when and how often to retrieve" itself learnable; 2. Data: high-quality instruction data and click/session logs are equally critical; synthetic data must guard against knowledge leakage and distribution shift; 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation with human evaluation; 4. Product: latency, cost, explainability, and safety policies are hard constraints for industrial deployment — do not optimize academic benchmarks alone.

Limitations and Future Work

Likely limitations include: experiment scale bounded by GPU budget, benchmark mismatch with real user distributions, English-centric data leaving cross-lingual generalization unknown, and safety risks of agent systems on the open web. Future directions include more efficient test-time compute allocation, deeper integration with knowledge graphs and structured databases, and causal/fairness constraints for recommender systems.

Related Entries

• Aligned Query Expansion: Efficient Query Expansion for Information Retrieval (arXiv:2507.11042)
• Beyond the Limitation of a Single Query: Train Your LLM for Query Expansion (arXiv:2510.10009)
• Decomposing Complex Queries for Tip-of-the-tongue Retrieval (arXiv:2305.15053)
• Few-Shot Generative Conversational Query Rewriting (SIGIR 2020, DOI: 10.1145/3397271.3401323)
• Hierarchical Query Classification in E-commerce Search (WWW 2024)
• Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion (arXiv:2504.14175)

Glossary

| Term | Meaning | |------|---------| | IR | Information Retrieval | | RAG | Retrieval-Augmented Generation | | LTR | Learning to Rank | | nDCG | Normalized Discounted Cumulative Gain, a ranking quality metric | | Agentic Search | Modeling search as sequential decision-making and tool calls | | Gen-IR | Generative Information Retrieval |

Reference

• Original paper: LLM-QE: Improving Query Expansion by Aligning Large Language Models with Ranking Preferences, arXiv:2502.17057, February 2025.