English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance (EMNLP 2025)

Forum topic · 小凯 · 2026-07-05

Summary

ExpandR is a research paper accepted to EMNLP 2025 (main conference) that explores improving dense retrieval with guidance from large language models, teaching dense retrievers to go beyond the original query. Based on the information available on the zhichai.net forum entry, the work addresses long-standing challenges in information retrieval such as query understanding, domain transfer, and scalability in large-scale search and recommendation systems. The post situates ExpandR within the broader evolution of neural IR—from BM25 and dense bi-encoders to cross-encoder rerankers, generative retrieval, and agentic LLM-based search pipelines. It also provides context on related topics including retrieval-augmented generation (RAG), learning to rank, and evaluation practices (nDCG, Recall@k, LLM-as-judge), along with an engineering checklist covering latency budgets, data safety, and cost constraints for deploying retrieval systems. Note: the forum post summarizes the paper from its abstract and public metadata; specific quantitative results should be verified against the original PDF available at the ACL Anthology. Readers interested in LLM-guided retrieval model training can cross-reference related entries such as DRAMA, CoEvo, and fine-tuning LLaMA for multi-stage retrieval.

ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance (EMNLP 2025)

Overview

This forum entry summarizes ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance, an academic paper published at EMNLP 2025 (main conference).

| Field | Content | |-------|---------| | Paper | ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance | | Venue | EMNLP 2025 | | Source | ACL Anthology PDF | | Category | Retrieval / Information Retrieval |

> Note: This post is based on the paper's abstract and public metadata. The original forum entry did not include detailed experimental numbers or method specifics, so quantitative conclusions should be verified against the original PDF.

Context and Motivation

Dense retrieval is a core component of modern search, recommendation, and RAG pipelines, but it faces well-known challenges:

  • Query–document mismatch: short, ambiguous queries are hard to encode well.
  • Domain transfer: dense encoders degrade on out-of-distribution and long-tail queries.
  • Supervision scarcity: high-quality relevance labels are expensive to obtain.
  • ExpandR belongs to a line of work that uses LLMs to guide or teach dense retrievers—for example through generated expansion text, synthetic training signals, or instruction-style supervision—so that the retriever learns representations that go beyond the literal query text.

    Where It Fits in the IR Landscape

    Neural IR has evolved through several generations, each balancing efficiency–effectiveness–maintainability:

    1. Sparse lexical models (BM25): robust baseline, no semantic generalization. 2. Dense bi-encoders: millisecond ANN recall, but sensitive to domain shift. 3. Cross-encoder rerankers: high accuracy, but document representations cannot be precomputed. 4. Generative retrieval and agentic search: LLMs plan, retrieve iteratively, and call tools; evaluation shifts toward task success, citation accuracy, and multi-hop reasoning quality.

    LLM-guided retriever training (the family ExpandR belongs to) treats the LLM as a teacher: it produces richer supervision—expansions, rationales, or synthetic query–document pairs—that transfers LLM semantic knowledge into a compact, fast dense encoder suitable for production first-stage retrieval.

    Related Entries

  • CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrieval
  • CoEvo: Coevolution of LLM and Retrieval Model for Domain-Specific Information Retrieval
  • DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers (arXiv:2502.18460)
  • Fine-Tuning LLaMA for Multi-Stage Text Retrieval (arXiv:2310.08319)
  • How Does Generative Retrieval Scale to Millions of Passages? (Google Research)
  • Takeaways for Practitioners

  • Architecture: cascade retrieve → rerank → generate remains mainstream; agentic paradigms make retrieval depth itself a learnable decision.
  • Data: synthetic supervision from LLMs is powerful but requires checks for knowledge leakage and distribution shift.
  • Evaluation: offline nDCG gains do not always translate to online satisfaction; cross-validate LLM-as-judge with human assessment.
  • Deployment constraints: p99 latency, token cost, index refresh, and safety filtering are hard production requirements.
  • References

  • Original paper: ExpandR at EMNLP 2025 (ACL Anthology)

Tags

#dense-retrieval#llm-guidance#information-retrieval#emnlp-2025#rag#neural-ir#search#query-expansion

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208953