activity
20242026
collaborators

8 papers

cs.AI2026

Superficial Beliefs in LLM Decision-Making

Gabriel Freedman, Francesca Toni

We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic underlying decision structure…

cs.AI2026

Neurosymbolic Learning for Inference-Time Argumentation

Gabriel Freedman, Adam Dejl, Adam Gould +4

Claim verification is an important problem in high-stakes settings, including health and finance. When information underpinning claims is incomplete or conflicting, uncertain answe…

cs.CL2025

Evaluating Uncertainty Quantification Methods in Argumentative Large Language Models

Kevin Zhou, Adam Dejl, Gabriel Freedman +3

Research in uncertainty quantification (UQ) for large language models (LLMs) is increasingly important towards guaranteeing the reliability of this groundbreaking technology. We ex…

cs.CL2025

Pub-Guard-LLM: Detecting Retracted Biomedical Articles with Reliable Explanations

Lihu Chen, Shuojie Fu, Gabriel Freedman +6

A significant and growing number of published scientific articles is found to involve fraudulent practices, posing a serious threat to the credibility and safety of research in fie…

cs.CL2025

MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification

Ming Pok Ng, Junqi Jiang, Gabriel Freedman +2

Leveraging outputs from multiple large language models (LLMs) is emerging as a method for harnessing their power across a wide range of tasks while mitigating their capacity for ma…

cs.AI2025

Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs

Gabriel Freedman, Francesca Toni

Advances in the general capabilities of large language models (LLMs) have led to their use for information retrieval, and as components in automated decision systems. A faithful re…