When a large language model solves a mathematical problem, its reasoning is largely hierarchical, and the solution often branches at a few tokens where the next-token entropy is high. Such tree-like structure embeds in hyperbolic space with far lower distortion than in Euclidean space. Activation steering, however, usu...
Ze-Yong Zhang, Tung Sum Thomas Kwok, Teng-Fei Ma et al.· 0 citations
Low-Entropy Discrete Flow (LEDFlow), a training-free sampler that adaptively orders absorption by local entropy, is proposed, and it is shown that, under entropy-error regularity, selecting the lowest-entropy positions under a fixed absorption count minimizes an upper bound on the conditional term.
Tung Sum Thomas Kwok, Yi-Dong Ouyang, Yingjia Wan et al.· 0 citations
FinInteract, a bilingual (English/Chinese) benchmark of 173 instances that pairs each question with a default and an intended interpretation across a five-category ambiguity taxonomy, and grades whether an agent elicits the right clarification and then integrates it, finds that conditioning on the ambiguity category im...
Xin-Yu Wang, Tung Sum Thomas Kwok, Zhenghan Tai et al.· 0 citations
Financial QA systems are typically improved before deployment through better retrieval, prompting, or agent coordination, leaving their reliability behavior fixed thereafter. In practice, new SEC-filing questions repeatedly expose heterogeneous errors in period, entity, evidence use, and calculation. Existing self-impr...
Yanzhang Ma, Zhenghan Tai, Han-Wei Wu et al.· 0 citations
FinSAgent is proposed, an evidence-grounded multi-agent framework that reframes SEC filing QA as corpus-aligned retrieval planning and corrects both ends with a single principle: inject corpus-side conditioning wherever model priors would otherwise dominate.
Jijun Chi, Zhenghan Tai, Han-Wei Wu et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
