Large Language Models (LLMs) for Text-to-SQL frequently generate queries with syntax errors, invalid identifier references, or violations of SQL scoping and typing rules. Repairing these errors is a program correctness problem, yet existing approaches rely on Execution Feedback (EF), whose symptom-level, dialect-specif...
Zhi-Hao Guo, Zong-Han Wu, Yi Shao et al.· 0 citations
The proposed method HalluTracer, which averages layer-wise probe logits to predict truthfulness before decoding, achieves the highest area under the receiver operating characteristic curve (AUROC) in 23 of 24 model--benchmark pairs among the compared methods.
Zhi-Hao Guo, Zong-Han Wu, Huan Huo et al.· 0 citations
Looped Transformers offer a parameter-efficient route to test-time scaling by reusing shared layers for iterative latent reasoning. However, additional iterations can reduce support for a reference answer, leaving unclear whether an update's direction is locally unhelpful or its full displacement moves too far. We stud...
Zhi-Hao Guo, Zong-Han Wu, Hai-Zhou Du et al.· 1 citation
HalluTracer is introduced, a detection framework that reads and aggregates truthfulness evidence across every layer of the forward pass before the model emits any answer token, recasts hallucination detection from a layer-selection problem into a depth-aggregation problem governed by the geometric sparsity of the truth...
Zhi-Hao Guo, Zong-Han Wu, Huan Huo et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.