This work revisit hallucination in MLLMs from the perspective of reasoning generation dynamics and proposes an entropy-aware self-introspective framework for MLLM reasoning, arguing that entropy is not merely a static measure of uncertainty but a structured signal that reflects how modality information is integrated th...
Jia-Qi Deng, Zhe Fu, Ya-Kun Chen et al.· 0 citations
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
Artificial intelligence (AI) is reshaping labor markets, yet its effects on wage distribution and the underlying mechanisms remain insufficiently understood. Conventional analytical approaches are limited in their ability to directly examine the dynamic evolution of worker behavior and income distribution under sustain...
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
SPMC, a training framework that identifies grounding-responsive heads and selectively regularizes their text-to-image attention, demonstrates that targeted guidance of sparse and implicit visual evidence pathways can directly improve multimodal reasoning.
Jia-Qi Deng, Zong-Han Wu, Zhan Heng 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
This work establishes a principled paradigm shift toward reliability-aware multi-modal learning for drug discovery by performing integrated representation learning across multiple modalities, and proposes Cross-Modal Subspace Alignment (CMSA), which treats incomplete knowledge graphs as recoverable signals, synthesizin...
Xiaodong Zhu, Longjun Song, Shi-Ying Zeng et al.· IEEE journal of biomedical a...· 0 citations
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...
Mint-Agent Team, Kun Wang, Gavin Zhang et al.· 0 citations
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.