Lune

ACL Findings2025

Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queries

Ganlin Xu, Zhoujia Zhang, Wangyi Mei, Jiaqing Liang, Weijia Lu, Xiaodong Zhang, Zhifei Yang, Xiaofeng Ma, Yanghua Xiao, Deqing Yang

Abstract

Information retrieval plays a crucial role in resource localization. Current dense retrievers retrieve the relevant documents within a corpus via embedding similarities, which compute similarities between dense vectors mainly depending on word co-occurrence between queries and documents, but overlook the real query intents. Thus, they often retrieve numerous irrelevant documents. Particularly in the scenarios of complex queries such as negative-constraint queries, their retrieval performance could be catastrophic. To address the issue, we propose a neuro-symbolic information retrieval method, namely NS-IR, that leverages firstorder logic (FOL) to optimize the embeddings of naive natural language by considering the logical consistency between queries and documents. Specifically, we introduce two novel techniques, logic alignment and connective constraint, to rerank candidate documents, thereby enhancing retrieval relevance. Furthermore, we construct a new dataset NegConstraint including negative-constraint queries to evaluate our NS-IR's performance on such complex IR scenarios. Our extensive experiments demonstrate that NS-IR not only achieves superior zero-shot retrieval performance on web search and lowresource retrieval tasks, but also performs better on negative-constraint queries. Our scource code and dataset are available at https:// github.com/xgl-git/NS-IR-main.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Precise Zero-Shot Dense Retrieval without Relevance Labels cites Dense Passage Retrieval for Open-Domain Question Answering
  • Precise Zero-Shot Dense Retrieval without Relevance Labels cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
  • ComLQ: Benchmarking Complex Logical Queries in Information Retrieval cites Precise Zero-Shot Dense Retrieval without Relevance Labels
  • ComLQ: Benchmarking Complex Logical Queries in Information Retrieval cites Dense Passage Retrieval for Open-Domain Question Answering
  • Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval cites Dense Passage Retrieval for Open-Domain Question Answering
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. ComLQ: Benchmarking Complex Logical Queries in Information RetrievalGanlin Xu, Zhitao Yin, Linghao Zhang, Jiaqing Liang et al.AAAI 2026

Builds on17

  1. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalLee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang et al.ICLR 2021 · 1,547 citations
  2. Precise Zero-Shot Dense Retrieval without Relevance LabelsLuyu Gao, Xueguang Ma, Jimmy Lin, Jamie CallanACL 2023 · 211 citations
  3. Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations
  4. Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language ModelsHaoran Wang, Kai ShuEMNLP Findings 2023 · 42 citations
  5. LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic ProversTheo Olausson, Alex Gu, Benjamin Lipkin, Cedegao E. Zhang et al.EMNLP 2023 · 37 citations

Related papers

  1. LinE: Logical Query Reasoning over Hierarchical Knowledge GraphsZijian Huang, Meng-Fen Chiang, Wang-Chien LeeKDD 2022 · 17 citations
  2. LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense RetrievalYanzhen Shen, Sihao Chen, Xueqiang Xu, Yunyi Zhang et al.EMNLP 2025 · 1 citation
  3. Spherical Embeddings for Atomic Relation Projection Reaching Complex Logical Query AnsweringChau D. M. Nguyen, Tim French, Michael Stewart, Melinda Hodkiewicz et al.WWW 2025 · 1 citation
  4. SConE: Simplified Cone Embeddings with Symbolic Operators for Complex Logical QueriesChau D. M. Nguyen, Tim French, Wei Liu, Michael StewartACL Findings 2023 · 3 citations
  5. Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge GraphsHongyu Ren, Jure LeskovecNeurIPS 2020 · 267 citations
Dusk over the sea between two cliffs drawn in fine vertical lines