4 papers
Scaling Trends for Lie Detector Oversight in Preference Learning
Oskar J. Hollinsworth, Ann-Kathrin Dombrowski, Sam Adam-Day +2
Deceptive behavior in LLMs is costly to monitor and prevent, motivating approaches such as Scalable Oversight via Lie Detectors (SOLiD) (Cundy & Gleave, 2025), which uses lie detec…
Convergence Laws for Extensions of First-Order Logic with Averaging
Sam Adam-Day, Michael Benedikt, Alberto Larrauri
For many standard models of random structure, first-order logic sentences exhibit a convergence phenomenon on random inputs. The most well-known example is for random graphs with c…
Neural Interactive Proofs
Lewis Hammond, Sam Adam-Day
We consider the problem of how a trusted, but computationally bounded agent (a 'verifier') can learn to interact with one or more powerful but untrusted agents ('provers') in order…
Almost Surely Asymptotically Constant Graph Neural Networks
Sam Adam-Day, Michael Benedikt, Ä°smail Ä°lkan Ceylan +1
We present a new angle on the expressive power of graph neural networks (GNNs) by studying how the predictions of real-valued GNN classifiers, such as those classifying graphs prob…