106 citations · 636 across the 106 of their papers we have counts for
5 papers · 1 filter
PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean
Jiyuan Tan, Vasilis Syrgkanis, Jose Blanchet
Even a carefully proofread paper can leave small gaps in its proofs or its stated assumptions. We introduce PaperFormalizer, a Lean-based agentic pipeline that helps authors find a…
Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection
Keertana Chidambaram, Andrew Ilyas, Vasilis Syrgkanis
Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model "actor" is inspected by a "monitor" (often another language model) for signs of…
CausalReasoningBenchmark: A Real-World Benchmark for Disentangled Evaluation of Causal Identification and Estimation
Ayush Sawarni, Jiyuan Tan, Vasilis Syrgkanis
Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effect (ATE). This approach conflate…
Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences
Keertana Chidambaram, Karthik Vinary Seetharaman, Vasilis Syrgkanis
Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference…
Predicting Long Term Sequential Policy Value Using Softer Surrogates
Hyunji Nam, Allen Nie, Ge Gao +2
Off-policy policy evaluation (OPE) estimates the outcome of a new policy using historical data collected from a different policy. However, existing OPE methods cannot handle cases…