Thomas Icard

Computer Science · Physical Sciences

19h-index3.5kcitations100works0.42yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Logic, Reasoning, and Knowledge(33), Bayesian Modeling and Causal Inference(30), Semantic Web and Ontologies(16), Advanced Algebra and Logic(16), Topic Modeling(14)

Publications100 total

Transcoder Adapters for Reasoning-Model Diffing
arXiv (Cornell University)·2026Open Access
Transcoder Adapters for Reasoning-Model Diffing
ArXiv.org·2026Open Access
Counterfactual Spaces
ArXiv.org·2026Open Access
Counterfactual Spaces
arXiv (Cornell University)·2026Open Access
Simple concepts and meanings: adequacy from below
Meaning a journal of linguistics and philosophy·2025Open Access
Language models cannot reliably distinguish belief from knowledge and fact
Nature Machine Intelligence·2025· 3 cited
<i>Inquiry Under Bounds</i> , by David Thorstad
Mind·2025
Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
arXiv (Cornell University)·2025Open Access
A Communication-First Account of Explanation
arXiv (Cornell University)·2025Open Access
Looking back to plan ahead: Causal judgments as a sampling approximation for action effectiveness
2025Open Access
When AI meets counterfactuals: the ethical implications of counterfactual world simulation models
AI and Ethics·2025· 1 citedOpen Access
Modeling Discrimination with Causal Abstraction
arXiv (Cornell University)·2025Open Access
Belief in the Machine: Investigating Epistemological Blind Spots of Language Models
arXiv (Cornell University)·2024· 3 citedOpen Access
Anticipating the Risks and Benefits of Counterfactual World Simulation Models (Extended Abstract)
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2024Open Access
On probabilistic and causal reasoning with summation operators
Journal of Logic and Computation·2024
Do as I explain: Explanations communicate optimal interventions
2024Open Access
On Probabilistic and Causal Reasoning with Summation Operators
arXiv (Cornell University)·2024Open Access
A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
arXiv (Cornell University)·2024Open Access
Anticipating the risks and benefits of counterfactual world simulation models
2023· 2 citedOpen Access
Probing the quantitative–qualitative divide in probabilistic reasoning
Annals of Pure and Applied Logic·2023· 10 citedOpen Access
page 1 of 5Next →

Frequent Co-authors

Wesley H. Holliday(10), Joshua Knobe(7), Tobias Gerstenberg(6), Duligur Ibeling(5), Noah D. Goodman(3), Jonathan F. Kominsky(3), Fiery Cushman(3), Tomohiro Hoshi(3), Matthew Harrison‐Trainor(3), Lawrence S. Moss(3), Rishi Bommasani(2), Drew A. Hudson(2), Niladri S. Chatterji(2), Esin Durmus(2), Neel Guha(2), Tatsunori Hashimoto(2), Peter Henderson(2), Omar Khattab(2), Ananya Kumar(2), Faisal Ladhak(2)