activity
20242026
collaborators

5 papers

cs.PL2026

All for one and none forall: Compiling polymorphic relations without monomorphization

Dmitri Volkov, Yafei Yang, Chung-Chieh Shan

We present a new approach for implementing polymorphism for bottom-up relational languages that avoids monomorphization. We begin by introducing semiringKanren, a bottom-up weighte…

cs.AI2025

Misalignment Bounty: Crowdsourcing AI Agent Misbehavior

Rustem Turtayev, Natalia Fedorova, Oleg Serikov +3

Advanced AI systems sometimes act in ways that differ from human intent. To gather clear, reproducible examples, we ran the Misalignment Bounty: a crowdsourced project that collect…

cs.PL2025

Committing to the bit: Relational programming with semiring arrays and SAT solving

Dmitri Volkov, Yafei Yang, Chung-chieh Shan

We propose semiringKanren, a relational programming language where each relation expression denotes a semiring array. We formalize a type system that restricts the arrays to finite…

cs.LG2025

Resurrecting saturated LLM benchmarks with adversarial encoding

Igor Ivanov, Dmitrii Volkov

Recent work showed that small changes in benchmark questions can reduce LLMs' reasoning and recall. We explore two such changes: pairing questions and adding more answer options, o…

cs.CR2024

BadGPT-4o: stripping safety finetuning from GPT models

Ekaterina Krupkina, Dmitrii Volkov

We show a version of Qi et al. 2023's simple fine-tuning poisoning technique strips GPT-4o's safety guardrails without degrading the model. The BadGPT attack matches best white-box…