21 citations · 64 across the 50 of their papers we have counts for
8 papers · 1 filter
Unveiling the Implicit Toxicity in Large Language Models
Jiaxin Wen, Pei Ke, Hao Sun +4
The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent st…
CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
Jinfeng Zhou, Zhuang Chen, Dazhen Wan +14
In this paper, we present CharacterGLM, a series of models built upon ChatGLM, with model sizes ranging from 6B to 66B parameters. Our CharacterGLM is designed for generating Chara…
AlignBench: Benchmarking Chinese Alignment of Large Language Models
Xiao Liu, Xuanyu Lei, Shengyuan Wang +15
Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants. However, the effective evaluation of alignment for emerging Ch…
CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation
Pei Ke, Bosi Wen, Zhuoer Feng +9
Since the natural language processing (NLP) community started to make large language models (LLMs) act as a critic to evaluate the quality of generated texts, most of the existing…
Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
Zhexin Zhang, Junxiao Yang, Pei Ke +3
While significant attention has been dedicated to exploiting weaknesses in LLMs through jailbreaking attacks, there remains a paucity of effort in defending against these attacks.…
Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
Jiale Cheng, Xiao Liu, Kehan Zheng +5
Large language models (LLMs) have shown impressive success in various applications. However, these models are often not well aligned with human intents, which calls for additional…
Language Model Decoding as Direct Metrics Optimization
Haozhe Ji, Pei Ke, Hongning Wang +1
Despite the remarkable advances in language modeling, current mainstream decoding methods still struggle to generate texts that align with human texts across different aspects. In…
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
Zhibin Gou, Zhihong Shao, Yeyun Gong +5
Large language models have made significant progress in various language tasks, yet they still struggle with complex mathematics. In this paper, we propose ToRA a series of Tool-in…