SMT-LLM builds a constraint graph from PyPI metadata and AST-derived imports, solves it with Z3, and uses LLM imputation only when needed, resolving 83.6% of HG2.9K snippets versus PLLM's 54.8% while cutting median time by 6.3x and LLM calls by 11x.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
LLMVD.js uses LLM agents to confirm 84% of taint-style vulnerabilities on public benchmarks (vs. <22% for prior tools) and generates validated exploits for 36 of 260 new packages (vs. ≤2 for traditional tools).
Once4All synthesizes LLM-based generators from extracted SMT grammars and populates formula skeletons to fuzz Z3 and cvc5, discovering 43 confirmed bugs with 40 fixed.
PLanet is a DSL that formalizes assignment procedures via matrix algebra operators, enabling static analysis of testable causal queries under explicit assumptions.
EquivFusion unifies equivalence checking across hardware design levels by lowering PyTorch, C/C++, Chisel, Verilog, and netlists via MLIR into SMT-LIB, BTOR2, and AIGER formats.
A grammar-constrained counterfactual refinement framework resolves inconsistencies in safety operational rules for an autonomous driving system while staying syntactically valid.
A meta-level neuro-symbolic layer uses LLMs to synthesize, consolidate, and verify minimal necessary-and-sufficient first-order causal rules from human-specified goals and principles, demonstrated in two autonomous-driving proof-of-concept scenarios.
citing papers explorer
-
Towards Neuro-symbolic Causal Rule Synthesis, Verification, and Evaluation Grounded in Legal and Safety Principles
A meta-level neuro-symbolic layer uses LLMs to synthesize, consolidate, and verify minimal necessary-and-sufficient first-order causal rules from human-specified goals and principles, demonstrated in two autonomous-driving proof-of-concept scenarios.