Logic-Parametric Neuro-Symbolic NLI: Controlling Logical Formalisms for Verifiable LLM Reasoning

• URL: http://arxiv.org/abs/2601.05705v1
• Date: Fri, 09 Jan 2026 10:47:30 GMT
• Title: Logic-Parametric Neuro-Symbolic NLI: Controlling Logical Formalisms for Verifiable LLM Reasoning
• Authors: Ali Farjami, Luca Redondi, Marco Valentino,
• Abstract summary: We propose a logic-parametric framework for neuro-symbolic natural language inference.<n>We embed a range of classical and non-classical formalisms into higher-order logic.<n>We show that logic-internal strategies can consistently improve performance.
• Score: 13.291627429657412
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) and theorem provers (TPs) can be effectively combined for verifiable natural language inference (NLI). However, existing approaches rely on a fixed logical formalism, a feature that limits robustness and adaptability. We propose a logic-parametric framework for neuro-symbolic NLI that treats the underlying logic not as a static background, but as a controllable component. Using the LogiKEy methodology, we embed a range of classical and non-classical formalisms into higher-order logic (HOL), enabling a systematic comparison of inference quality, explanation refinement, and proof behavior. We focus on normative reasoning, where the choice of logic has significant implications. In particular, we compare logic-external approaches, where normative requirements are encoded via axioms, with logic-internal approaches, where normative patterns emerge from the logic's built-in structure. Extensive experiments demonstrate that logic-internal strategies can consistently improve performance and produce more efficient hybrid proofs for NLI. In addition, we show that the effectiveness of a logic is domain-dependent, with first-order logic favouring commonsense reasoning, while deontic and modal logics excel in ethical domains. Our results highlight the value of making logic a first-class, parametric element in neuro-symbolic architectures for more robust, modular, and adaptable reasoning.

Related papers

• Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning [17.5066777599458]
  Symbolic logical reasoning is a critical yet underexplored capability of large language models (LLMs)<n>We show that logical reasoning performance remains stable within a regime but collapses abruptly beyond a critical logical depth.<n>We propose Neuro-Symbolic Curriculum Tuning, a principled framework that adaptively aligns natural language with logical symbols to establish a shared representation.
  arXiv  Detail & Related papers  (2026-01-06T10:38:25Z)
• DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models [58.439517684779936]
  This paper proposes a new classical logic benchmark DivLogicEval, consisting of natural sentences composed of diverse statements in a counterintuitive way.<n>To ensure a more reliable evaluation, we also introduce a new evaluation metric that mitigates the influence of bias and randomness inherent in Large Language Models.
  arXiv  Detail & Related papers  (2025-09-19T04:40:46Z)
• A Reduction of Input/Output Logics to SAT [51.82266520875928]
  Deontic logics are formalisms for reasoning over norms, obligations, permissions and prohibitions.<n>In this paper, an automation approach for I/O logics is presented that makes use of suitable reductions to propositional satisfiability problems.
  arXiv  Detail & Related papers  (2025-08-22T09:22:26Z)
• Categorical Construction of Logically Verifiable Neural Architectures [0.0]
  Neural networks excel at pattern recognition but struggle with reliable logical reasoning, often violating basic logical principles during inference.<n>We develop a categorical framework that systematically constructs neural architectures with provable logical guarantees.<n>The framework provides mathematical foundations for trustworthy AI systems, with applications to theorem proving, formal verification, and safety-critical reasoning tasks requiring verifiable logical behavior.
  arXiv  Detail & Related papers  (2025-08-02T04:30:05Z)
• Logic Agent: Enhancing Validity with Logic Rule Invocation [24.815341366820753]
  Chain-of-Thought prompting has emerged as a pivotal technique for augmenting the inferential capabilities of language models during reasoning tasks.<n>This paper introduces the Logic Agent (LA), an agent-based framework aimed at enhancing the validity of reasoning processes in Large Language Models.
  arXiv  Detail & Related papers  (2024-04-28T10:02:28Z)
• 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)
• Discourse-Aware Graph Networks for Textual Logical Reasoning [142.0097357999134]
  Passage-level logical relations represent entailment or contradiction between propositional units (e.g., a concluding sentence) We propose logic structural-constraint modeling to solve the logical reasoning QA and introduce discourse-aware graph networks (DAGNs) The networks first construct logic graphs leveraging in-line discourse connectives and generic logic theories, then learn logic representations by end-to-end evolving the logic relations with an edge-reasoning mechanism and updating the graph features.
  arXiv  Detail & Related papers  (2022-07-04T14:38:49Z)
• Strong Equivalence of Logic Programs with Ordered Disjunction: a Logical Perspective [1.160208922584163]
  Logic Programs with Ordered Disjunction (LPODs) extend classical logic programs with the capability of expressing preferential disjunctions. In this paper we obtain a purely logical characterization of strong equivalence of LPODs as logical equivalence in a four-valued logic. We provide a new proof of the coNP-completeness of strong equivalence for LPODs, which has an interest in its own right since it relies on the special structure of such programs.
  arXiv  Detail & Related papers  (2022-05-10T13:33:32Z)
• Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks [65.23508422635862]
  We propose learning rules with the recently proposed logical neural networks (LNN) Compared to others, LNNs offer strong connection to classical Boolean logic. Our experiments on standard benchmarking tasks confirm that LNN rules are highly interpretable.
  arXiv  Detail & Related papers  (2021-12-06T19:38:30Z)
• Logical Neural Networks [51.46602187496816]
  We propose a novel framework seamlessly providing key properties of both neural nets (learning) and symbolic logic (knowledge and reasoning) Every neuron has a meaning as a component of a formula in a weighted real-valued logic, yielding a highly intepretable disentangled representation. Inference is omni rather than focused on predefined target variables, and corresponds to logical reasoning.
  arXiv  Detail & Related papers  (2020-06-23T16:55:45Z)

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.