Shaohang Wei

4 papers · 2025–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

ACL (3) NAACL (1)

Top co-authors

Houfeng Wang (3) Feifan Song (3) Wen Luo (3) Guangyue Peng (2) Wei Li (2) Yakun Zhu (1) Xiaofan Zhang (1) Kui Xue (1) Tianyu Liu (1) Yuxuan Fan (1)

Research topics

Artificial Intelligence (4) Core AI (4) Natural Language Processing (2) Deep Learning (1) Machine Learning (1) Core Methods (1) Generation (1) Learning Paradigms (1) Learning Types (1) Resources & Methods (1)

Keywords

large language model (2) text generation (1) tool selection (1) hallucination detection (1) human preference (1) internal representation (1) llm agent (1) decoding method (1) open-ended generation (1) dynamic focus decoding (1) stochastic decoding (1) clinical assessment (1) attention knockout (1) open-ended text generation (1) alignment tax (1) medical calculator (1) nested tool calling (1) weak-to-strong decoding (1) factual text generation (1) diverse text generation (1)

Papers

Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations ACL 2026 MeNTi: Bridging Medical Calculator and LLM Agent with Nested Tool Calling NAACL 2025 Odysseus Navigates the Sirens’ Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation ACL 2025 Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding ACL 2025