activity
20232025
most citedInductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs

4 citations · 11 across the 7 of their papers we have counts for

collaborators

7 papers

cs.AI2025

Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates

Hy Dang, Tianyi Liu, Zhuofeng Wu +9

Large language models (LLMs) have demonstrated strong reasoning and tool-use capabilities, yet they often fail in real-world tool-interactions due to incorrect parameterization, po…

cs.LG20242 cited

Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models

Yilun Jin, Zheng Li, Chenwei Zhang +19

Online shopping is a complex multi-task, few-shot learning problem with a wide and evolving range of entities, relations, and tasks. However, existing models and benchmarks are com…

cs.AI20244 cited

Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs

Kewei Cheng, Jingfeng Yang, Haoming Jiang +9

Reasoning encompasses two typical types: deductive reasoning and inductive reasoning. Despite extensive research into the reasoning capabilities of Large Language Models (LLMs), mo…

cs.DB2024

Relational Database Augmented Large Language Model

Zongyue Qin, Chen Luo, Zhengyang Wang +2

Large language models (LLMs) excel in many natural language processing (NLP) tasks. However, since LLMs can only incorporate new knowledge through training or supervised fine-tunin…

cs.IR20242 cited

Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond

Tianxin Wei, Bowen Jin, Ruirui Li +8

Developing a universal model that can effectively harness heterogeneous resources and respond to a wide range of personalized needs has been a longstanding community aspiration. Ou…

cs.CL2024

Knowledge Editing on Black-box Large Language Models

Xiaoshuai Song, Zhengyang Wang, Keqing He +4

Knowledge editing (KE) aims to efficiently and precisely modify the behavior of large language models (LLMs) to update specific knowledge without negatively influencing other knowl…