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

Domain-specific Question Answering with Hybrid Search (arXiv 2412.03736)

Forum topic · 小凯 · 2026-07-05

Summary

This arXiv paper (2412.03736, December 2024), authored by Dewang Sultania, Zhaoyu Lu, Twisha Naik, Franck Dernoncourt, David Seunghyun Yoon, Sanat Sharma, and colleagues (14 authors in total), addresses domain-specific question answering using hybrid search. Hybrid search combines sparse retrieval methods such as BM25 with dense embedding-based retrieval to improve recall and precision when answering questions over specialized corpora where off-the-shelf language models lack reliable knowledge. The paper sits at the intersection of information retrieval and retrieval-augmented generation (RAG), covering the standard cascade of retriever, re-ranker, and generator components, evaluation protocols with datasets like MS MARCO and BEIR, and metrics such as nDCG@10, MRR, and Recall@k. For engineers, the practical takeaways include combining lexical and vector search, controlling latency and cost through cascading and early stopping, and validating answer quality with citation checks. Readers should consult the PDF for exact quantitative results. Related work includes Azure AI Search hybrid retrieval, COS-Mix similarity fusion, and Facebook scoped search modernization.

Domain-specific Question Answering with Hybrid Search (arXiv 2412.03736)

Overview

  • Paper: Domain-specific Question Answering with Hybrid Search
  • Authors: Dewang Sultania, Zhaoyu Lu, Twisha Naik, Franck Dernoncourt, David Seunghyun Yoon, Sanat Sharma, et al. (14 authors)
  • Published: December 2024 (arXiv)
  • Topic area: Hybrid search vs. vector search; domain-specific question answering
  • Key points

  • The work targets question answering over specialized domains, where generic LLMs lack reliable, up-to-date knowledge and must rely on external retrieval.
  • It uses hybrid search, combining sparse (e.g., BM25-style lexical) retrieval with dense embedding-based retrieval to improve both recall and precision over specialized corpora.
  • Context: why hybrid search matters

    Classic search stacks follow a funnel: recall (retrieval), discrimination (ranking), and presentation (generation). Dense retrieval enables millisecond-level ANN recall but is sensitive to domain shift and long-tail queries; cross-encoder re-rankers are accurate but cannot precompute document representations; hybrid approaches mitigate these weaknesses by fusing lexical and semantic signals.

    In the LLM era, RAG and agentic search extend external knowledge access from a one-shot retrieval step into an iterative, verifiable, plannable process. Evaluation correspondingly shifts from static nDCG toward task success rate, citation accuracy, and multi-hop reasoning completeness.

    Typical pipeline structure

    1. Input & representation: encode queries, documents, and user context as dense or sparse representations, or structured prompts. 2. Core modules: retriever, re-ranker, planner, memory, tool interfaces, chained or parallelized per task. 3. Learning strategies: supervised fine-tuning, contrastive learning, distillation, RL, or synthetic data bootstrapping. 4. Inference strategies: single-shot retrieval, iterative retrieval, parallel sub-queries, early stopping, and budget control.

    Evaluation

  • Datasets/benchmarks: MS MARCO, BEIR, Natural Questions, and domain-specific corpora.
  • Metrics: nDCG@10, MRR, Recall@k, Hit@k, task success rate, latency, and token cost.
  • Baselines: BM25, dense retrieval, cross-encoder re-ranking, retrieval-free LLMs, commercial search APIs.
  • Note: exact quantitative results should be verified against the paper's PDF.

    Engineering checklist

    | Check | Question | Suggestion | |-------|----------|------------| | Data | Does training/indexing data contain PII? | Partitioned indexes, anonymization, rollback-able embedding versions | | Latency | What is the p99 budget? How many retrieval steps? | Cascade + early stop, query caching, async re-ranking | | Quality | Do offline gains translate to online satisfaction? | Interleaving experiments, human audits, citation checks | | Safety | Does open retrieval introduce poisoning/bias? | Source allowlists, adversarial detection, output filtering | | Cost | Token and GPU cost per query? | Small-model routing, distillation, sparse+dense hybrid |

    Glossary

  • 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 with tool calls
  • Gen-IR — Generative Information Retrieval
  • Related entries

  • Azure AI Search: Outperforming vector search with hybrid retrieval
  • COS-Mix: Cosine Similarity and Distance Fusion (arXiv 2406.00638)
  • Deep Retrieval at CheckThat! 2025 (arXiv 2505.23250)
  • Efficient Knowledge Graph Construction and Retrieval (arXiv 2507.03226)
  • Hybrid Hierarchical Retrieval for Open-Domain QA
  • Modernizing Facebook Scoped Search (arXiv 2509.13603)
  • References

  • Original paper: https://arxiv.org/abs/2412.03736

Tags

#hybrid-search#question-answering#information-retrieval#rag#vector-search#bm25#llm#arxiv

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/178208742