From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement

• URL: http://arxiv.org/abs/2604.05539v1
• Date: Tue, 07 Apr 2026 07:38:16 GMT
• Title: From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement
• Abstract summary: We present a neurosymbolic approach, combining symbolic and subsymbolic artificial intelligence, to offer documents in regulated public institutions.<n>We employ a language model to extract information and then aggregate with an LTN to make an auditable decision.<n>Our experiments on a real corpus show that the proposed pipeline achieves performance comparable to existing models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We present a neurosymbolic approach, i.e., combining symbolic and subsymbolic artificial intelligence, to validating offer documents in regulated public institutions. We employ a language model to extract information and then aggregate with an LTN (Logic Tensor Network) to make an auditable decision. In regulated public institutions, decisions must be made in a manner that is both factually correct and legally verifiable. Our neurosymbolic approach allows existing domain-specific knowledge to be linked to the semantic text understanding of language models. The decisions resulting from our pipeline can be justified by predicate values, rule truth values, and corresponding text passages, which enables rule checking based on a real corpus of offer documents. Our experiments on a real corpus show that the proposed pipeline achieves performance comparable to existing models, while its key advantage lies in its interpretability, modular predicate extraction, and explicit support for XAI (Explainable AI).

Related papers

• BoolXLLM: LLM-Assisted Explainability for Boolean Models [6.97075461976982]
  Interpretable machine learning aims to provide transparent models whose decision-making processes can be readily understood by humans.<n>Main challenges remain in practice: (i) selecting semantically meaningful features and (ii) translating formal logical rules into accessible explanations.<n>We propose BoolXLLM as a hybrid framework that integrates Large Language Models into the end-to-end pipeline of Boolean rule learning.
  arXiv  Detail & Related papers  (2026-05-12T13:58:20Z)
• From Legal Texts to Defeasible Deontic Logic via LLMs: A Study in Automated Semantic Analysis [1.5749416770494706]
  We present a novel approach to the automated semantic analysis of legal texts using large language models (LLMs)<n>We propose a structured pipeline that segments complex normative language into atomic snippets, extracts deontic rules, and evaluates them for syntactic and semantic coherence.
  arXiv  Detail & Related papers  (2025-06-10T15:25:19Z)
• Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning [29.745218855471787]
  Tokenization is a necessary component within the current architecture of many language mod-els.<n>We argue that tokenization is necessary for reasonably human-like language performance.<n>We discuss implications for architectural choices, meaning construction, the primacy of language for thought.
  arXiv  Detail & Related papers  (2024-12-14T18:18:52Z)
• LatentQA: Teaching LLMs to Decode Activations Into Natural Language [72.87064562349742]
  We introduce LatentQA, the task of answering open-ended questions about model activations in natural language.<n>We propose Latent Interpretation Tuning (LIT), which finetunes a decoder LLM on a dataset of activations and associated question-answer pairs.<n>Our decoder also specifies a differentiable loss that we use to control models, such as debiasing models on stereotyped sentences and controlling the sentiment of generations.
  arXiv  Detail & Related papers  (2024-12-11T18:59:33Z)
• ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering [0.0]
  Neurosymbolic approaches can add robustness to opaque neural systems by incorporating explainable symbolic representations. We propose systemname, a novel neurosymbolic framework, to improve robustness and reliability of large language models. Our work opens a new area of neurosymbolic generative AI text validation and user personalization.
  arXiv  Detail & Related papers  (2024-09-17T22:34:33Z)
• Learning Phonotactics from Linguistic Informants [54.086544221761486]
  Our model iteratively selects or synthesizes a data-point according to one of a range of information-theoretic policies. We find that the information-theoretic policies that our model uses to select items to query the informant achieve sample efficiency comparable to, or greater than, fully supervised approaches.
  arXiv  Detail & Related papers  (2024-05-08T00:18:56Z)
• APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning [73.3035118224719]
  We propose APOLLO, an adaptively pretrained language model that has improved logical reasoning abilities. APOLLO performs comparably on ReClor and outperforms baselines on LogiQA.
  arXiv  Detail & Related papers  (2022-12-19T07:40:02Z)
• The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding [65.34601470417967]
  We describe a hybrid architecture for dialogue response generation that combines the strengths of neural language modeling and rule-based generation. Our experiments show that this system outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.
  arXiv  Detail & Related papers  (2022-09-16T09:00:49Z)
• Lex Rosetta: Transfer of Predictive Models Across Languages, Jurisdictions, and Legal Domains [40.58709137006848]
  We analyze the use of Language-Agnostic Sentence Representations in sequence labeling models using Gated Recurrent Units (GRUs) that are transferable across languages. We found that models generalize beyond the contexts on which they were trained. We found that training the models on multiple contexts increases robustness and improves overall performance when evaluating on previously unseen contexts.
  arXiv  Detail & Related papers  (2021-12-15T04:53:13Z)
• Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand? [87.20342701232869]
  We investigate the abilities of ungrounded systems to acquire meaning. We study whether assertions enable a system to emulate representations preserving semantic relations like equivalence. We find that assertions enable semantic emulation if all expressions in the language are referentially transparent. However, if the language uses non-transparent patterns like variable binding, we show that emulation can become an uncomputable problem.
  arXiv  Detail & Related papers  (2021-04-22T01:00:17Z)
• Coreferential Reasoning Learning for Language Representation [88.14248323659267]
  We present CorefBERT, a novel language representation model that can capture the coreferential relations in context. The experimental results show that, compared with existing baseline models, CorefBERT can achieve significant improvements consistently on various downstream NLP tasks.
  arXiv  Detail & Related papers  (2020-04-15T03:57:45Z)

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.