dorsal/arxiv
View SchemaLogic-Parametric Neuro-Symbolic NLI: Controlling Logical Formalisms for Verifiable LLM Reasoning
| Authors | Ali Farjami, Luca Redondi, Marco Valentino |
|---|---|
| Categories | |
| ArXiv ID | 2601.05705vv1 |
| URL | https://arxiv.org/abs/2601.05705 |
| 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.
{
"annotation_id": "f18366f5-67c4-4dca-a9fd-08fd7534fc0f",
"date_created": "2026-02-17T05:53:05.053000Z",
"date_modified": "2026-02-17T05:53:05.053000Z",
"file_hash": "4edad0bfb9c7d4101ac8ae52f4342906c27bcd7f34a749e179c02bc76b9136c7",
"private": false,
"record": {
"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\u0027s 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.",
"arxiv_id": "2601.05705",
"authors": [
"Ali Farjami",
"Luca Redondi",
"Marco Valentino"
],
"categories": [
"cs.AI",
"cs.CL",
"cs.LO"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "Logic-Parametric Neuro-Symbolic NLI: Controlling Logical Formalisms for Verifiable LLM Reasoning",
"url": "https://arxiv.org/abs/2601.05705",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "f49446fe-681b-43b2-b091-06be6ff70c70",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}