Enhancing Retrieval Systems with Inference-Time Logical Reasoning

• URL: http://arxiv.org/abs/2503.17860v1
• Date: Sat, 22 Mar 2025 20:40:18 GMT
• Title: Enhancing Retrieval Systems with Inference-Time Logical Reasoning
• Authors: Felix Faltings, Wei Wei, Yujia Bao,
• Abstract summary: We propose a novel inference-time logical reasoning framework that explicitly incorporates logical reasoning into the retrieval process.<n>Our method extracts logical reasoning structures from natural language queries and then composes the individual cosine similarity scores to formulate the final document scores.
• Score: 9.526027847179677
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traditional retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity within an embedding space. While efficient and scalable, this approach often fails to handle complex queries involving logical constructs such as negations, conjunctions, and disjunctions. In this paper, we propose a novel inference-time logical reasoning framework that explicitly incorporates logical reasoning into the retrieval process. Our method extracts logical reasoning structures from natural language queries and then composes the individual cosine similarity scores to formulate the final document scores. This approach enables the retrieval process to handle complex logical reasoning without compromising computational efficiency. Our results on both synthetic and real-world benchmarks demonstrate that the proposed method consistently outperforms traditional retrieval methods across different models and datasets, significantly improving retrieval performance for complex queries.

Related papers

• ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge Graphs [14.25887925588904]
  We propose a retrieval-augmented framework that combines query-aware neighborhood retrieval with large language model (LLM) chain-of-thought reasoning.<n>ROG decomposes a multi-operator query into a sequence of single-operator sub-queries.<n> Intermediate answer sets are cached and reused across steps, improving consistency on deep reasoning chains.
  arXiv  Detail & Related papers  (2026-02-02T17:45:43Z)
• OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning [51.58235452818926]
  We introduce OrLog, a neuro-symbolic retrieval framework that decouples predicate-level plausibility estimation from logical reasoning.<n>A large language model (LLM) provides plausibility scores for atomic predicates in one decoding-free forward pass, from which a probabilistic reasoning engine derives the posterior probability of query satisfaction.
  arXiv  Detail & Related papers  (2026-01-30T15:31:58Z)
• Capturing P: On the Expressive Power and Efficient Evaluation of Boolean Retrieval [0.0]
  Modern information retrieval is transitioning from simple document filtering to complex, neuro-symbolic reasoning.<n>We present a formal Retrieval Language ($mathcalL_R$) based on Directed Acyclic Graphs (DAGs) and prove it captures complexity class $mathbfP$.<n>This work establishes the theoretical foundation for turning the index into a general-purpose computational engine.
  arXiv  Detail & Related papers  (2026-01-26T18:07:40Z)
• A Large Language Model Based Method for Complex Logical Reasoning over Knowledge Graphs [16.929901817693334]
  Reasoning over knowledge graphs (KGs) with first-order logic (FOL) queries is challenging due to the inherent incompleteness of real-world KGs.<n>We propose ROG (Reasoning Over knowledge Graphs with large language models), an ensemble-style framework that combines query-aware KG neighborhood retrieval with large language model (LLM)-based chain-of-thought reasoning.
  arXiv  Detail & Related papers  (2025-12-22T07:01:05Z)
• CORG: Generating Answers from Complex, Interrelated Contexts [57.213304718157985]
  In a real-world corpus, knowledge frequently recurs across documents but often contains inconsistencies due to ambiguous naming, outdated information, or errors. Previous research has shown that language models struggle with these complexities, typically focusing on single factors in isolation. We introduce Context Organizer (CORG), a framework that organizes multiple contexts into independently processed groups.
  arXiv  Detail & Related papers  (2025-04-25T02:40:48Z)
• BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language? [88.29075896295357]
  We first investigate whether current retrieval systems can comprehend the Boolean logic implied in language. Through extensive experimental results, we draw the conclusion that current dense retrieval systems do not fully understand Boolean logic in language. We propose a contrastive continual training method that serves as a strong baseline for the research community.
  arXiv  Detail & Related papers  (2024-11-19T05:19:53Z)
• H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables [56.73919743039263]
  This paper introduces a novel algorithm that integrates both symbolic and semantic (textual) approaches in a two-stage process to address limitations. Our experiments demonstrate that H-STAR significantly outperforms state-of-the-art methods across three question-answering (QA) and fact-verification datasets.
  arXiv  Detail & Related papers  (2024-06-29T21:24:19Z)
• A Surprisingly Simple yet Effective Multi-Query Rewriting Method for Conversational Passage Retrieval [14.389703823471574]
  We propose the use of a neural query rewriter to generate multiple queries and show how to integrate those queries in the passage retrieval pipeline efficiently. The main strength of our approach lies in its simplicity: it leverages how the beam search algorithm works and can produce multiple query rewrites at no additional cost.
  arXiv  Detail & Related papers  (2024-06-27T07:43:03Z)
• SparseCL: Sparse Contrastive Learning for Contradiction Retrieval [87.02936971689817]
  Contradiction retrieval refers to identifying and extracting documents that explicitly disagree with or refute the content of a query. Existing methods such as similarity search and crossencoder models exhibit significant limitations. We introduce SparseCL that leverages specially trained sentence embeddings designed to preserve subtle, contradictory nuances between sentences.
  arXiv  Detail & Related papers  (2024-06-15T21:57:03Z)
• FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering [46.41364317172677]
  Large language models (LLMs) are often challenged by generating erroneous or hallucinated responses.<n>We propose a unified framework, FiDeLiS, designed to improve the factuality of LLM responses by anchoring answers to verifiable reasoning steps retrieved from a KG.
  arXiv  Detail & Related papers  (2024-05-22T17:56:53Z)
• Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension [80.99865844249106]
  We propose a holistic graph network (HGN) which deals with context at both discourse level and word level, as the basis for logical reasoning. Specifically, node-level and type-level relations, which can be interpreted as bridges in the reasoning process, are modeled by a hierarchical interaction mechanism.
  arXiv  Detail & Related papers  (2023-06-21T07:34:27Z)
• Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual Samples [30.079030298066847]
  State-of-the-art methods based on pre-trained models have achieved remarkable performance on the standard test dataset. We question whether these methods really learn how to perform logical reasoning, rather than just relying on the spurious correlations between the headers of the tables and operators of the logical form. We propose two approaches to reduce the model's reliance on the shortcut.
  arXiv  Detail & Related papers  (2022-10-16T14:14:53Z)
• Refining Labelled Systems for Modal and Constructive Logics with Applications [0.0]
  This thesis serves as a means of transforming the semantics of a modal and/or constructive logic into an 'economical' proof system. The refinement method connects two proof-theoretic paradigms: labelled and nested sequent calculi. The introduced refined labelled calculi will be used to provide the first proof-search algorithms for deontic STIT logics.
  arXiv  Detail & Related papers  (2021-07-30T08:27:15Z)
• Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text [65.24325614642223]
  We propose to understand logical symbols and expressions in the text to arrive at the answer. Based on such logical information, we put forward a context extension framework and a data augmentation algorithm. Our method achieves the state-of-the-art performance, and both logic-driven context extension framework and data augmentation algorithm can help improve the accuracy.
  arXiv  Detail & Related papers  (2021-05-08T10:09:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.