technique

neurosymbolic learning

techniqueactiveneurosymbolic-learning-8895a10a·1 events·first seen 28d ago

Aliases: neurosymbolic learning

Co-occurring entities

large language models Inference-Time Argumentation (ITA)ternary claim verification formal argumentation semantics

More like this (12)

soft-label learning Imitation Learning meta-learning Q-learning Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents Soft Q-Learning in-context learning large neural network training self-play reinforcement learning neural network image classifiers contrastive learning Structured Interactive Learning

Recent events (1)

5arXiv · cs.AI·28d ago·source ↗

Neurosymbolic Learning for Inference-Time Argumentation in Claim Verification

This paper introduces Inference-Time Argumentation (ITA), a trainable neurosymbolic framework for ternary claim verification (true/false/uncertain) that integrates formal argumentation semantics with LLM training. The framework uses argumentation semantics both to guide LLM training for argument generation and scoring, and to compute final predictions deterministically from explicit argumentative structures. Unlike conventional reasoning models that rely on potentially unfaithful post-hoc explanations, ITA produces verdicts that are faithful by construction to the underlying arguments. Experiments on two ternary claim verification datasets show ITA outperforms argumentative baselines and competes with non-argumentative direct-prediction approaches.

Evaluation and Benchmarking AI Safety Research large language models Inference-Time Argumentation (ITA)ternary claim verification +3 more