We have 4 of 11 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
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.
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...
Mint-Agent, a family of finance-native agentic models designed around these two scales of financial intelligence, is presented, establishing a path toward trustworthy financial intelligence in which domain expertise, long-horizon execution, and auditable evidence are jointly engineered as a unified foundation for front...
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...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
