7 papers
ReSyn: Autonomously Scaling Synthetic Environments for Reasoning Models
Andre He, Nathaniel Weir, Kaj Bostrom +4
Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising approach for training reasoning language models (RLMs) by leveraging supervision from verifiers. Al…
VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning
Vikash Singh, Darion Cassel, Nathaniel Weir +2
Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge. We present a neurosymbolic…
VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks
Yu Feng, Nathaniel Weir, Kaj Bostrom +5
LLMs can perform multi-step reasoning through Chain-of-Thought (CoT), but they cannot reliably verify their own logic. Even when they reach correct answers, the underlying reasonin…
A Neurosymbolic Approach to Natural Language Formalization and Verification
Chenyang An, Sam Bayless, Stefano Buliani +27
Large Language Models perform well at natural language interpretation and reasoning, but their lack of formal correctness guarantees limits their adoption in regulated industries l…
Learning to Triage Vulnerability Reports from Program Analysis: An Empirical Study in Node.js
Ronghao Ni, Aidan Z. H. Yang, Min-Chien Hsu +5
Program analysis tools often produce large volumes of candidate vulnerability reports that require costly manual review, creating a practical challenge: how can security analysts p…
A Community-driven vision for a new Knowledge Resource for AI
Vinay K Chaudhri, Chaitan Baru, Brandon Bennett +29
The long-standing goal of creating a comprehensive, multi-purpose knowledge resource, reminiscent of the 1984 Cyc project, still persists in AI. Despite the success of knowledge re…
Uncovering Information Flow Policy Violations in C Programs
Darion Cassel, Yan Huang, Limin Jia
Programmers of cryptographic applications written in C need to avoid common mistakes such as sending private data over public channels, modifying trusted data with untrusted functi…