Yuji Zhang
@Yuji_Zhang_NLP
Postdoc@UIUC, advised by Prof. Heng Ji @hengjinlp and Prof. Chengxiang Zhai. Robust and trustworthy LLMs. LLM hallucination. LLM knowledge. LLM reasoning.
🔍New findings of knowledge overshadowing! Why do LLMs hallucinate over all true training data? 🤔Can we predict hallucinations even before model training or inference? 🚀Check out our new preprint: [arxiv.org/pdf/2502.16143] The Law of Knowledge Overshadowing: Towards…
![Yuji_Zhang_NLP's tweet image. 🔍New findings of knowledge overshadowing! Why do LLMs hallucinate over all true training data? 🤔Can we predict hallucinations even before model training or inference?
🚀Check out our new preprint: [arxiv.org/pdf/2502.16143] The Law of Knowledge Overshadowing: Towards…](https://pbs.twimg.com/media/Gk-lqV5WAAAnkqS.jpg)
![Yuji_Zhang_NLP's tweet image. 🔍New findings of knowledge overshadowing! Why do LLMs hallucinate over all true training data? 🤔Can we predict hallucinations even before model training or inference?
🚀Check out our new preprint: [arxiv.org/pdf/2502.16143] The Law of Knowledge Overshadowing: Towards…](https://pbs.twimg.com/media/Gk-lqV4WIAAW4KU.jpg)
![Yuji_Zhang_NLP's tweet image. 🔍New findings of knowledge overshadowing! Why do LLMs hallucinate over all true training data? 🤔Can we predict hallucinations even before model training or inference?
🚀Check out our new preprint: [arxiv.org/pdf/2502.16143] The Law of Knowledge Overshadowing: Towards…](https://pbs.twimg.com/media/Gk-lqV6XMAAe_vZ.jpg)
![Yuji_Zhang_NLP's tweet image. 🔍New findings of knowledge overshadowing! Why do LLMs hallucinate over all true training data? 🤔Can we predict hallucinations even before model training or inference?
🚀Check out our new preprint: [arxiv.org/pdf/2502.16143] The Law of Knowledge Overshadowing: Towards…](https://pbs.twimg.com/media/Gk-lqV5WEAAn1Gf.jpg)
Checkout our latest paper! Atomic reasoning makes LLMs smarter, not harder🎉Unlocking efficient, transferable skills for verifying complex scientific claims with minimal data. 🧠🚀
🧠Let’s teach LLMs to learn smarter, not harder💥[arxiv.org/pdf/2506.06972] 🤖How can LLMs verify complex scientific information efficiently? 🚀We propose modular, reusable atomic reasoning skills that reduce LLMs’ cognitive load to verify scientific claims with little data.…
What’s is the agent? What is the optimal behavior to achieve the predefined goal? And how to learn that behavior policy? We formally introduce a systematic Theory of Agent (ToA), analogous to the cognitive framework of Theory of Mind (ToM). Where ToM refers to the ability to…
Can LLMs make rational decisions like human experts? 📖Introducing DecisionFlow: Advancing Large Language Model as Principled Decision Maker We introduce a novel framework that constructs a semantically grounded decision space to evaluate trade-offs in hard decision-making…
🔥Today is submission deadline (June 6th AoE) of our 𝐀𝐂𝐋 𝟐𝟎𝟐𝟓 𝐰𝐨𝐫𝐤𝐬𝐡𝐨𝐩: 𝐓𝐨𝐰𝐚𝐫𝐝𝐬 𝐊𝐧𝐨𝐰𝐥𝐞𝐝𝐠𝐞𝐚𝐛𝐥𝐞 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬!🔥 🔗workshop website: knowledgeable-lm.github.io 🔗 submission portal: openreview.net/group?id=aclwe… 🏆 The Best Paper…
Great to see the wonderful series of work that @WangCarrey has been leading at UIUC. We also had a fun collaboration recently together with my incoming PhD student Shijue. Check out our latest release "AdaCtrl: Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting"…
📢 New Paper Drop: From Solving to Modeling! LLMs can solve math problems — but can they model the real world? 🌍 📄 arXiv: arxiv.org/pdf/2505.15068 💻 Code: github.com/qiancheng0/Mod… Introducing ModelingAgent, a breakthrough system for real-world mathematical modeling with LLMs.
🤖 New preprint: We propose ten principles of AI agent economics, offering a framework to understand how AI agents make decisions, influence social interactions, and participate in the broader economy. 📜 Paper: arxiv.org/abs/2505.20273
We are extremely excited to announce mCLM, a Modular Chemical Language Model that is friendly to automatable block-based chemistry and mimics bilingual speakers by “code-switching” between functional molecular modules and natural language descriptions of the functions. 1/2
Imagine AI assistants on your smart glasses or laptop proactively bridging your info gaps! 🗺️ Entering a building? Get instant floor plans for seamless navigation. 🧑💻 In lectures? Receive concise explanations to stay on track. Our new preprint introduces Just-In-Time…
What are the capabilities of current Conversational Agents? What challenges persist and what actually we should expect from these agents as a next step? 🚀We are excited to share our recent survey: ✨ A Desideratum for Conversational Agents: Capabilities, Challenges, and Future…
Why allocate the same number of visual tokens to a blank image and a complex landscape? Introducing DyMU: a training-free algorithm that makes any ViT visual encoder dynamic-length and plug-and-play with downstream VLMs. 🚀 🔗 Project Page: mikewangwzhl.github.io/dymu/
🚀 ToolRL unlocks LLMs' true tool mastery! The secret? Smart rewards > more data. 📖 Introducing newest paper: ToolRL: Reward is all Tool Learning Needs Paper Link: arxiv.org/pdf/2504.13958 Github Link: github.com/qiancheng0/Too…
Today is the day! Welcome to our 2nd workshop on Knowledgeable Foundation Models in Room 112. Come and talk with these wonderful speakers @ehovy @Wenpeng_Yin @RICEric22 @Lianhuiq @liharryzhang @HuajieShaoML ! Special thanks to our organizers @ZoeyLi20 @megamor2 @XiaozhiWangNLP…
🚀 Introducing VLM²-Bench! A simple yet essential ability that we use in daily life. But when tackling vision-centric tasks without relying on prior knowledge, can VLMs perform well? 🤔 🔗 Project Page: vlm2-bench.github.io More details below! 👇 (1/n)
🚀Join us tomorrow in Room 122A for our 2nd AAAI @RealAAAI AI4Research workshop🧪! We have an exciting lineup of presentations from our amazing invited speakers—don’t miss out! #AI4Research #AAAI2025 sites.google.com/view/ai4resear…
Excited to share our latest on multimodal AI and agents for drug design and therapeutic reasoning #AAAI2025 @RealAAAI 📅 Monday, 9 AM – AI2ASE: AI to Accelerate Science and Engineering, ai-2-ase.github.io/schedule/ 📅 Tuesday, 10 AM – AI4Research: Knowledge-Grounded Scientific…