activity
20232026
most citedLatent Causal Probing: A Formal Perspective on Probing with Causal Models of Data

1 citations · 2 across the 6 of their papers we have counts for

collaborators

6 papers

cs.GT2026

Nash Equilibria with Derangement Degree Probabilities

Edan Orzech, Martin Rinard

We prove for every the existence of an -player game in normal form with integer payoffs that has a unique Nash equilibrium, which is fully mixed. In the equilibrium, eac…

cs.GT2025

Nash Equilibria with Irradical Probabilities

Edan Orzech, Martin Rinard

We present for every an -player game in normal form with payoffs in that has a unique, fully mixed, Nash equilibrium in which all the probability weights are…

cs.SE2025

Evaluating the Generalization Capabilities of Large Language Models on Code Reasoning

Rem Yang, Julian Dai, Nikos Vasilakis +1

We assess how the code reasoning abilities of large language models (LLMs) generalize to different kinds of programs. We present techniques for obtaining in- and out-of-distributio…

cs.CL2024★ 1 cited

Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data

Charles Jin, Martin Rinard

As language models (LMs) deliver increasing performance on a range of NLP tasks, probing classifiers have become an indispensable technique in the effort to better understand their…

cs.GT2024★ 1 cited

Edge-dominance games on graphs

Farid Arthaud, Edan Orzech, Martin Rinard

We consider zero-sum games in which players move between adjacent states, where in each pair of adjacent states one state dominates the other. The states in our game can represent…

cs.GT2023

Randomness Requirements and Asymmetries in Nash Equilibria

Edan Orzech, Martin Rinard

In general, Nash equilibria in normal-form games may require players to play (probabilistically) mixed strategies. We define a measure of the complexity of finite probability distr…