Author

Ben He

h-index 10 View on Semantic Scholar

We have 3 of 32 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.

#natural language process... Jul 2025

Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction

AOE (Arranged and Organized Extraction), a bilingual benchmark that evaluates LLMs'ability to distill long-form, multi-document inputs into structured tables, is introduced, revealing that structured extraction from long contexts remains a fundamental challenge - an"Area of Effect"(AOE) that impacts all tested systems.

Tian-Yun Zhong, Guozhao Mo, Yan-Jiang Liu et al. · arXiv.org · 0 citations

Navigating the Inﬁnite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration

Inspired by the human cognitive planning process, HintNav-igator achieves state-of-the-art performance among open-source LLM agents, surpassing proprietary model Claude-3.5 Sonnet on the WebArena benchmark.

Guozhao Mo, Yan-Jiang Liu, Yafei Shi et al. · 0 citations

#natural language process... Jan 2026

Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering

AdaRAS (Adaptive Reasoning Activation Steering), a lightweight test-time framework that improves reasoning reliability by selectively intervening on neuron activations during inference, enhancing incorrect reasoning traces while avoiding degradation on already-correct cases.

Fang Dong, Zu-Ming Yan, Xuri Ge et al. · arXiv.org · 5 citations