University of Notre Dame

Wonderful University

Instructing LLMs to solve math word prob better: - Mask a condition, Predict the condition with initial answer, Verify the answer, Rectify to avoid wrong answer(s) (AAAI'24): wzy6642.github.io/prp.github.io/ - Identify and Ignore Irrelevant Conditions (NAACL'24): wzy6642.github.io/I3C.github.io/

🔎How to unleash LLM's inherent ability to detect and rectify incorrect responses without external feedback? 👀Check out our latest pre-print and find out how to progressively identify and correct false responses. Link: arxiv.org/abs/2405.14092

🐲 Check out our new preprint! 📷CodeTaxo is a novel method for taxonomy expansion via prompting #LLMs. Link: arxiv.org/pdf/2408.09070 Thanks to all collaborators: Yuyang Bai, Zhaoxuan Tan, Zhenyu Wu and Meng Jiang from Notre Dame CSE; Shangbin Feng from UW NLP!

Attending #EMNLP2024 to present: Pluralism through Modular LLMs Wed 1030 arxiv.org/abs/2406.15951 Abstain with Multilingual Feedback w/ Wenxuan Ding Tue 1600 arxiv.org/abs/2406.15948 LLM Graph Reasoning w/ Yizhuo Zhang Heng Wang Tue 1100 arxiv.org/abs/2406.15992 Chat!

Excited to present at #EMNLP next week on personalized LLM. Also, I’m looking for an internship—let’s connect! Personalized PEFT: arxiv.org/abs/2402.04401 Nov 13, 10:30, Riverfront Parameter Composition for Personalized PEFT: arxiv.org/abs/2406.10471 Nov 12, 11:00, Riverfront

See you at #EMNLP! My students will present their LLM studies about Reasoning, Self-Correct, Personalization, QG, and Instruction Following. They are looking for internships / full-time jobs.

Title: Enhancing Mathematical Reasoning in LLMs by Stepwise Correction Track: NLP Applications 2 Location: Hall M.1 Time: 09:00–10:30 Presentation Number: 6 Feel free to reach out if you have any questions or would like to connect!😃