# Neurosymbolic Learning for Inference-Time Argumentation

arXiv: https://arxiv.org/abs/2605.20098 · HTML: https://mlsanity.com/paper/2605.20098/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 19 May 2026.

## Builds on (most cited first, 25 of 25)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [Know Your Limits: A Survey of Abstention in Large Language Models](https://mlsanity.com/paper/2407.18418/) (2024)
- [Large Language Models Must Be Taught to Know What They Don't Know](https://mlsanity.com/paper/2406.08391/) (2024)
- [Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models](https://mlsanity.com/paper/2305.13712/) (2023)
- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [Argumentative Large Language Models for Explainable and Contestable Claim Verification](https://mlsanity.com/paper/2405.02079/) (2024)
- [Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements](https://mlsanity.com/paper/2402.10614/) (2024)
- [I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token](https://mlsanity.com/paper/2412.06676/) (2024)
- [Claim Verification in the Age of Large Language Models: A Survey](https://mlsanity.com/paper/2408.14317/) (2024)
- [FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents](https://mlsanity.com/paper/2411.05764/) (2024)
- [Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning](https://mlsanity.com/paper/2502.14765/) (2025)
- [Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs](https://mlsanity.com/paper/2504.13644/) (2025)
- [Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning](https://mlsanity.com/paper/2604.22074/) (2026)
- [Neuro-Argumentative Learning with Case-Based Reasoning](https://mlsanity.com/paper/2505.15742/) (2025)
- [Evaluating Uncertainty Quantification Methods in Argumentative Large Language Models](https://mlsanity.com/paper/2510.02339/) (2025)
- [Argumentation for Explainable and Globally Contestable Decision Support with LLMs](https://mlsanity.com/paper/2603.14643/) (2026)
- [Argumentative Reward Learning: Reasoning About Human Preferences](https://mlsanity.com/paper/2209.14010/) (2022)
- [Argumentation and Machine Learning](https://mlsanity.com/paper/2410.23724/) (2024)

## Built on by (most cited first, 2 of 2)

- [A Theory of Post-hoc Debate Judgement](https://mlsanity.com/paper/2608.19002/) (2026)
- [Embedding Models for Stance-Aware Argument Retrieval](https://mlsanity.com/paper/2608.28283/) (2026)

## Abstract (arXiv)

Claim verification is an important problem in high-stakes settings, including health and finance. When information underpinning claims is incomplete or conflicting, uncertain answers may be more appropriate than binary true or false classifications. In all cases, faithful explanations of the considerations determining the final verdict are crucial. We introduce inference-time argumentation (ITA), a trainable neurosymbolic framework for ternary claim verification in which a formal argumentation semantics giving the strength of claims is used both (i) to guide LLM training as models learn to generate arguments and assign them base scores (representing intrinsic strengths) and (ii) to compute ternary (true/false/uncertain) predictions from generated, scored arguments. As a result, at training time, argument generation and scoring can be optimised according to the quality of the induced argumentative predictions. Moreover, at inference time, the final prediction is faithful, by construction, to the arguments and scores determining the verdict, rather than being justified by a potentially unfaithful post-hoc reasoning trace as in conventional reasoning models. We finally show that, on two datasets for ternary claim verification, ITA improves upon argumentative baselines and can perform competitively against non-argumentative direct-prediction baselines, while providing verdicts that are computed deterministically from explicit, inspectable argumentative structures.