7 papers
Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study
Qiming Bao, Sherry J. H. Feng, Kim Chester Eugenio +1
Structure-preserving de-identification replaces protected health information (PHI) with realistic same-type surrogates -- "Anna S." becomes "Maria S.", not [NAME] -- so that clinic…
Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors
Qiming Bao, Xiaoxuan Fu, Michael Witbrock
Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic f…
RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization
Qiming Bao, Juho Leinonen, Paul Denny +1
Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators…
Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning
Qiming Bao, Alex Yuxuan Peng, Zhenyun Deng +10
Combining large language models with logical reasoning enhances their capacity to address problems in a robust and reliable manner. Nevertheless, the intricate nature of logical re…
Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation
Qiming Bao, Alex Yuxuan Peng, Tim Hartill +4
Combining deep learning with symbolic logic reasoning aims to capitalize on the success of both fields and is drawing increasing attention. Inspired by DeepLogic, an end-to-end mod…
Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning
Qiming Bao, Gael Gendron, Alex Yuxuan Peng +5
Large language models (LLMs), such as LLaMA, Alpaca, Vicuna, GPT-3.5 and GPT-4, have advanced the performance of AI systems on various natural language processing tasks to human-li…