OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning

• URL: http://arxiv.org/abs/2601.23085v1
• Date: Fri, 30 Jan 2026 15:31:58 GMT
• Title: OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning
• Authors: Mohanna Hoveyda, Jelle Piepenbrock, Arjen P de Vries, Maarten de Rijke, Faegheh Hasibi,
• Abstract summary: 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.
• Score: 51.58235452818926
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Resolving complex information needs that come with multiple constraints should consider enforcing the logical operators encoded in the query (i.e., conjunction, disjunction, negation) on the candidate answer set. Current retrieval systems either ignore these constraints in neural embeddings or approximate them in a generative reasoning process that can be inconsistent and unreliable. Although well-suited to structured reasoning, existing neuro-symbolic approaches remain confined to formal logic or mathematics problems as they often assume unambiguous queries and access to complete evidence, conditions rarely met in information retrieval. To bridge this gap, we introduce OrLog, a neuro-symbolic retrieval framework that decouples predicate-level plausibility estimation from logical reasoning: 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. We evaluate OrLog across multiple backbone LLMs, varying levels of access to external knowledge, and a range of logical constraints, and compare it against base retrievers and LLM-as-reasoner methods. Provided with entity descriptions, OrLog can significantly boost top-rank precision compared to LLM reasoning with larger gains on disjunctive queries. OrLog is also more efficient, cutting mean tokens by $\sim$90\% per query-entity pair. These results demonstrate that generation-free predicate plausibility estimation combined with probabilistic reasoning enables constraint-aware retrieval that outperforms monolithic reasoning while using far fewer tokens.

Related papers

• A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic [21.003276503456632]
  We propose a novel method to augment a logic problem with commonsense relations provided by the Large Language Models.<n>This involves a search procedure through potential commonsense assumptions to maximize the chance of finding useful facts.
  arXiv  Detail & Related papers  (2026-01-26T15:40:26Z)
• ComLQ: Benchmarking Complex Logical Queries in Information Retrieval [26.606215927237248]
  Information retrieval systems play a critical role in navigating information overload across various applications.<n>These benchmarks can not be used to sufficiently evaluate the performance of IR models on complex queries in real-world scenarios.<n>We propose a novel method leveraging large language models (LLMs) to construct a new IR dataset textbfComLQ for textbfComplex textbfLogical textbfQueries.
  arXiv  Detail & Related papers  (2025-11-15T02:58:21Z)
• Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning [55.55968342644846]
  Large Language Models (LLMs) achieve excellent performance in natural language reasoning tasks through pre-training on vast unstructured text.<n>We propose the textitLogits-to-Logic framework, which incorporates logits strengthening and logits filtering as core modules to correct logical defects in LLM outputs.
  arXiv  Detail & Related papers  (2025-11-11T07:08:27Z)
• Do LLMs Dream of Discrete Algorithms? [0.7646713951724011]
  Large Language Models (LLMs) have rapidly transformed the landscape of artificial intelligence.<n>Their reliance on probabilistic inference limits their effectiveness in domains requiring strict logical reasoning.<n>This paper proposes a neurosymbolic approach that augments LLMs with logic-based reasoning modules.
  arXiv  Detail & Related papers  (2025-06-29T22:03:01Z)
• LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval [54.2765452810124]
  We introduce LogiCoL, a logically-informed contrastive learning objective for dense retrievers.<n>We show that models trained with LogiCoL yield improvement both in terms of retrieval performance and logical consistency in the results.
  arXiv  Detail & Related papers  (2025-05-26T07:00:32Z)
• Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models [9.689096888732642]
  We propose Logic-of-Thought (LoT) prompting which employs propositional logic to generate expanded logical information descriptions.<n>LoT boosts the performance of various prompting methods with a striking margin across five logical reasoning tasks.
  arXiv  Detail & Related papers  (2024-09-26T04:59:45Z)
• Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning [89.89857766491475]
  We propose a curriculum-based logical-aware instruction tuning framework, named LACT.<n>Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition.<n> Experiments across widely used datasets demonstrate that LACT has substantial improvements(brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art.
  arXiv  Detail & Related papers  (2024-05-02T18:12:08Z)
• Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs [95.07757789781213]
  Two lines of approaches are adopted for complex reasoning with LLMs.<n>One line of work prompts LLMs with various reasoning structures, while the structural outputs can be naturally regarded as intermediate reasoning steps.<n>The other line of work adopt LLM-free declarative solvers to do the reasoning task, rendering higher reasoning accuracy but lacking interpretability due to the black-box nature of the solvers.<n>We present a simple extension to the latter line of work. Specifically, we showcase that the intermediate search logs generated by Prolog interpreters can be accessed and interpreted into human-readable reasoning.
  arXiv  Detail & Related papers  (2023-11-16T11:26:21Z)
• 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)
• Fuzzy Logic based Logical Query Answering on Knowledge Graph [37.039516386710716]
  We present FuzzQE, a fuzzy logic based query embedding framework for answering FOL queries over KGs. FuzzyQE follows fuzzy logic to define logical operators in a principled and learning free manner. Experiments on two benchmark datasets demonstrate that FuzzQE achieves significantly better performance in answering FOL queries.
  arXiv  Detail & Related papers  (2021-08-05T05:54:00Z)

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.