--- title: "Q2EI — paper by Sun et al. (2026) — summary and ideas" description: "They instead propose Generative Query Condensation (GQC), which compresses a query rather than enlarging it. 2 references." authors: ["Yixuan Sun", "Zhenqin Xu", "HanFeng Zhai", "Zishu Yu", "Xiaohui Peng"] year: 2026 venue: "Findings of the Association for Computational Linguistics: ACL 2026" source: "https://aclanthology.org/2026.findings-acl.1791/" doi: "10.18653/v1/2026.findings-acl.1791" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/sun-2026-q2ei-query-entity-inference-semantic/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sun-2026-q2ei-query-entity-inference-semantic/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/40/) / Q2EI: Query-to-Entity Inference for Semantic Condensation in Domain-Specific Retrieval # Q2EI: Query-to-Entity Inference for Semantic Condensation in Domain-Specific Retrieval **Authors:** Yixuan Sun, Zhenqin Xu, HanFeng Zhai, Zishu Yu and Xiaohui Peng · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1791/) · [PDF](https://aclanthology.org/2026.findings-acl.1791.pdf) · [DOI 10.18653/v1/2026.findings-acl.1791](https://doi.org/10.18653/v1/2026.findings-acl.1791) · [OpenAlex](https://openalex.org/W7166858490) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary Retrieval in specialized fields such as medicine and law often fails because users describe symptoms or situations in everyday language, while the relevant documents use expert terminology. Common LLM-based fixes like HyDE and Query2Doc lengthen the query with generated text. The authors show that this extra material dilutes the useful signal and shifts query embeddings away from the target. They instead propose Generative Query Condensation (GQC), which compresses a query rather than enlarging it. Their implementation, Q2EI, prompts an LLM (zero-shot or few-shot, without fine-tuning or a hand-built knowledge base) to infer the domain entity behind a lay query, such as "Botulism", and then builds a compact, entity-focused query around it. On MedQuAD and COLIEE, Q2EI outperforms strong baselines with both sparse and dense retrievers while using far fewer rewriting tokens. The work matters because it offers a cheap, interpretable pre-retrieval step that makes RAG more dependable in professional domains and degrades gracefully when the entity guess is wrong. ## Key points - **Headline gains:** On COLIEE, mE5 gains 3.35 nDCG@10 over the best baseline. On MedQuAD, BM25 gains 13.97 Recall@10 over the best baseline. BGE-M3 was also evaluated. - **Motivation experiment (mE5, MedQuAD):** Appending generated descriptions to queries hurts retrieval even when the text is relevant. Recall@10 falls from 86.88 to 77.94 with 100 added words and to 67.10 with 300 words. - **Correct entity inference:** When the inferred entity matches the target, Q2EI few-shot on mE5 reaches 52.11 nDCG@10, compared with 18.34 for HyDE and 22.53 for Q2D. - **Wrong entity inference:** When the inferred entity is incorrect, Q2EI still scores slightly better (6.61 vs. 4.82 for Q2D), suggesting that compact rewrites limit error amplification. - **Token cost per query on MedQuAD:** HyDE uses about 13,409 tokens and Q2D about 2,768. Q2EI uses about 905 tokens zero-shot (6.8% of HyDE) and about 1,718 few-shot (12.8% of HyDE). Code and data are released on GitHub (xu2023-ICT/Q2EI). *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 194 works · 23,906 citations - [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 147 works · 8,480 citations - [Institute of Computing Technology](https://md.research.elamur.ai/free/en/labs/institute-of-computing-technology/) — Research institute, Beijing, China · 51 works · 3,411 citations - [Hohai University](https://md.research.elamur.ai/free/en/universities/hohai-university/) — University, Nanjing, China · 2 works · 5 citations 📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works 🧭 Topics (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works ## Cite Cite as: Yixuan Sun, Zhenqin Xu, HanFeng Zhai, Zishu Yu and Xiaohui Peng. 2026. Q2EI: Query-to-Entity Inference for Semantic Condensation in Domain-Specific Retrieval. Findings of the Association for Computational Linguistics: ACL 2026. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{sun2026q2ei, title = {{Q2EI: Query-to-Entity Inference for Semantic Condensation in Domain-Specific Retrieval}}, author = {Yixuan Sun, Zhenqin Xu, HanFeng Zhai, Zishu Yu and Xiaohui Peng}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2026}, year = {2026}, doi = {10.18653/v1/2026.findings-acl.1791}, url = {https://doi.org/10.18653/v1/2026.findings-acl.1791} } ``` - [← previous PyraMathBench: Evaluating and Improving Mathematical Capability in Large Language Models](https://md.research.elamur.ai/free/en/papers/ouyang-2026-pyramathbench-evaluating-improving-mathematical-capability/) - [next → QAMAR: A New Fully Verified and Accurate Quranic Arabic Morphological Analysis Resource.](https://md.research.elamur.ai/free/en/papers/faqihi-2026-qamar-new-fully-verified-accurate/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/40/) ## References 2 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. \#\# Limitations Anthropic. 2025. Claude sonnet 4.5 system card. API version: claude-sonnet-4-5-20250929. [find](https://scholar.google.com/scholar?q=%5C%23%5C%23+Limitations+Anthropic%2E+2025%2E+Claude+sonnet+4%2E5+system+card%2E+API+version%3A+claude%2Dsonnet%2D4%2D5%2D20250929%2E) 2. While Q2EI demonstrates superior performance in specialized domain retrieval tasks, we acknowledge the following limitations, which also illuminate directions for future research. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Sh… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/) *Updated 1 November 2026*