2 citations · 7 across the 7 of their papers we have counts for
7 papers
When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
Junchen Li, Liang Xu, Qizhi Chen +6
Retrieval-Augmented Generation (RAG) systems are vulnerable to blocking attacks, in which poisoned documents cause large language models (LLMs) to refuse benign queries. Existing a…
Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
Chenyang Wang, Liang Wen, Shousheng Jia +2
While advancements in the reasoning abilities of LLMs have significantly enhanced their performance in solving mathematical problems, coding tasks, and general puzzles, their effec…
GeoSense: Evaluating Identification and Application of Geometric Principles in Multimodal Reasoning
Liangyu Xu, Yingxiu Zhao, Jingyun Wang +9
Geometry problem-solving (GPS), a challenging task requiring both visual comprehension and symbolic reasoning, effectively measures the reasoning capabilities of multimodal large l…
SuperCLUE-Fin: Graded Fine-Grained Analysis of Chinese LLMs on Diverse Financial Tasks and Applications
Liang Xu, Lei Zhu, Yaotong Wu +1
The SuperCLUE-Fin (SC-Fin) benchmark is a pioneering evaluation framework tailored for Chinese-native financial large language models (FLMs). It assesses FLMs across six financial…
Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning
Xiuqin Zhong, Shengyuan Yan, Gongqi Lin +5
In the context of online education, designing an automatic solver for geometric problems has been considered a crucial step towards general math Artificial Intelligence (AI), empow…
SuperCLUE-Math6: Graded Multi-Step Math Reasoning Benchmark for LLMs in Chinese
Liang Xu, Hang Xue, Lei Zhu +1
We introduce SuperCLUE-Math6(SC-Math6), a new benchmark dataset to evaluate the mathematical reasoning abilities of Chinese language models. SC-Math6 is designed as an upgraded Chi…
SC-Safety: A Multi-round Open-ended Question Adversarial Safety Benchmark for Large Language Models in Chinese
Liang Xu, Kangkang Zhao, Lei Zhu +1
Large language models (LLMs), like ChatGPT and GPT-4, have demonstrated remarkable abilities in natural language understanding and generation. However, alongside their positive imp…