Identifying Implicit Premises for Logical Reconstruction of Argument Graphs

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Xuyao Feng, Anthony Hunter
• Venue: arXiv: cs.CL
• Published: 2026-08-19
• Collected: 2026-08-20
• URL: http://arxiv.org/abs/2608.18821v1
• PDF: https://arxiv.org/pdf/2608.18821v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The authors propose a neuro-symbolic pipeline to generate implicit premises from natural language text, which can be translated into logical formulae to show the logical relationships between statements (entailment, contradiction, or neutrality). This method is evaluated on the Microtext Argumentative Corpus.

What the Document Says

• There's a challenge in logically reconstructing argument graphs from natural language text due to the prevalence of enthymemes (arguments with implicit premises)
• Existing methods for identifying enthymemes in text and missing premises in logical representations
• Proposal of a neuro-symbolic pipeline that uses large language models (LLMs) to generate intermediate implicit premises, translate into logical formulae, and show the logical relationships between them
• Evaluation of the approach on the Microtext Argumentative Corpus

Key Concepts Mentioned

• enthymeme
• logical reconstruction
• argument graph
• neuro-symbolic pipeline
• large language models (LLMs)
• logical formulae
• Microtext Argumentative Corpus

Claims Made by the Document

• The logical reconstruction of argument graphs from natural language text is challenging
• There's a need for methods to generate implicit premises for logical relationships
• The proposed pipeline can generate intermediate implicit premises and show the logical relationships

Evidence Used

• Text describes the challenges in logical reconstruction, the need for methods, and the proposed pipeline's ability

Methods / Approach

• Neuro-symbolic pipeline using large language models (LLMs) to generate intermediate implicit premises, translate into logical formulae, and show the logical relationships

Limitations Stated by the Authors

• The authors do not provide details about the specific LLM used or the exact methodology of translating implicit premises into logical formulae

Limitations Noted by the Agent

Agent interpretation — not from the source.

• The text does not mention any limitations in the evaluation process on the Microtext Argumentative Corpus

Open Questions

• What specific large language model is used in the proposed pipeline?
• How exactly are implicit premises translated into logical formulae?

Notes for Future Q&A

May include interpretation. Labeled where it does.

• The text does not mention the specific LLM used or the exact methodology of translating implicit premises into logical formulae

Raw Abstract / Excerpt

The logical reconstruction of argument graphs from natural language text is challenging because of the prevalence of enthymemes (i.e., arguments with implicit premises). There are natural language processing methods for identifying enthymemes in text, and there are symbolic methods based on abduction for identifying missing premises in a logical representation of enthymemes. However, there is a need for methods to generate implicit premises to logically show a known entailment or contradiction relationship between a pair of statements. To address this, we propose a neuro-symbolic pipeline that uses large language models (LLMs) to generate intermediate implicit premises that are translated into logical formulae and used with logical formulae representing explicit premises and explicit claims to show the logical relationships between them (entailment, contradiction, or neutrality). Our approach is evaluated on the Microtext Argumentative Corpus.