Search papers, labs, and topics across Lattice.
SemLoc is introduced as a novel fault localization framework that leverages LLMs to reason about program semantics and ground these inferences in a structured, executable representation. By converting free-form LLM reasoning into typed program anchors, SemLoc constructs a semantic violation spectrum that can be systematically analyzed to identify suspicious code locations. Experiments on the SemFault-250 dataset demonstrate that SemLoc significantly outperforms existing techniques, achieving a Top-1 accuracy of 42.8% and reducing inspection effort to 7.6% of executable lines.
LLMs can pinpoint semantic bugs that traditional methods miss, thanks to a new framework that turns their free-form reasoning into verifiable, executable code constraints.
Fault localization identifies program locations responsible for observed failures. Existing techniques rank suspicious code using syntactic spectra--signals derived from execution structure such as statement coverage, control-flow divergence, or dependency reachability. These signals collapse for semantic bugs, where failing and passing executions follow identical code paths and differ only in whether semantic intent is satisfied. Recent LLM-based approaches introduce semantic reasoning but produce stochastic, unverifiable outputs that cannot be systematically cross-referenced across tests or distinguish root causes from cascading effects. We present SemLoc, a fault localization framework based on structured semantic grounding. SemLoc converts free-form LLM reasoning into a closed intermediate representation that binds each inferred property to a typed program anchor, enabling runtime checking and attribution to program structure. It executes instrumented programs to construct a semantic violation spectrum--a constraint-by-test matrix--from which suspiciousness scores are derived analogously to coverage-based methods. A counterfactual verification step further prunes over-approximate constraints and isolates primary causal violations. We evaluate SemLoc on SemFault-250, a corpus of 250 Python programs with single semantic faults. SemLoc outperforms five coverage-, reduction-, and LLM-based baselines, achieving Top-1 accuracy of 42.8% and Top-3 of 68%, while reducing inspection to 7.6% of executable lines. Counterfactual verification provides an additional 12% accuracy gain and identifies primary causal semantic constraints.
