5 papers
Forethought: Verifiable Reasoning from Neurosymbolic Primitive Programming
Vishvesh Bhat, Jay Vaghasiya, Emmanuel Anaya Gonzalez
Current agentic workflows usually involve decomposing user requests into sequences of tool calls with correctly resolved parameters, the results of which are processed through reas…
Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective
Emmanuel Anaya Gonzalez, Sairam Vaidya, Kanghee Park +3
Constrained decoding enables Language Models (LMs) to produce samples that provably satisfy hard constraints. However, existing constrained-decoding approaches often distort the un…
HiLDe: Intentional Code Generation via Human-in-the-Loop Decoding
Emmanuel Anaya González, Raven Rothkopf, Sorin Lerner +1
While AI programming tools hold the promise of increasing programmers' capabilities and productivity to a remarkable degree, they often exclude users from essential decision-making…
Laurel: Unblocking Automated Verification with Large Language Models
Eric Mugnier, Emmanuel Anaya Gonzalez, Ranjit Jhala +2
Program verifiers such as Dafny automate proofs by outsourcing them to an SMT solver. This automation is not perfect, however, and the solver often requires hints in the form of as…
HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis
Shraddha Barke, Emmanuel Anaya Gonzalez, Saketh Ram Kasibatla +2
Many structured prediction and reasoning tasks can be framed as program synthesis problems, where the goal is to generate a program in a domain-specific language (DSL) that transfo…