21 citations · 64 across the 50 of their papers we have counts for
18 papers · 1 filter
The Superalignment of Superhuman Intelligence with Large Language Models
Minlie Huang, Yingkang Wang, Shiyao Cui +2
We have witnessed superhuman intelligence thanks to the fast development of large language models and multimodal language models. As the application of such superhuman models becom…
CharacterBench: Benchmarking Character Customization of Large Language Models
Jinfeng Zhou, Yongkang Huang, Bosi Wen +13
Character-based dialogue (aka role-playing) enables users to freely customize characters for interaction, which often relies on LLMs, raising the need to evaluate LLMs' character c…
Does RLHF Scale? Exploring the Impacts From Data, Model, and Method
Zhenyu Hou, Pengfan Du, Yilin Niu +7
This study explores the scaling properties of Reinforcement Learning from Human Feedback (RLHF) in Large Language Models (LLMs). Although RLHF is considered an important step in po…
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
Jiazheng Xu, Yu Huang, Jiale Cheng +19
Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimen…
Agent-SafetyBench: Evaluating the Safety of LLM Agents
Zhexin Zhang, Shiyao Cui, Yida Lu +4
As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those assoc…
SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Jiale Cheng, Xiao Liu, Cunxiang Wang +7
Instruction-following is a fundamental capability of language models, requiring the model to recognize even the most subtle requirements in the instructions and accurately reflect…
BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models
Xinyuan Wang, Victor Shea-Jay Huang, Renmiao Chen +4
While large language models (LLMs) exhibit remarkable capabilities across various tasks, they encounter potential security risks such as jailbreak attacks, which exploit vulnerabil…
Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning
Jiaxin Wen, Jian Guan, Hongning Wang +2
Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling co…
Language Models Learn to Mislead Humans via RLHF
Jiaxin Wen, Ruiqi Zhong, Akbir Khan +6
Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this p…
LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models
Jiayi Gui, Yiming Liu, Jiale Cheng +6
Large Language Models (LLMs) have demonstrated notable capabilities across various tasks, showcasing complex problem-solving abilities. Understanding and executing complex rules, a…
Benchmarking Complex Instruction-Following with Multiple Constraints Composition
Bosi Wen, Pei Ke, Xiaotao Gu +11
Instruction following is one of the fundamental capabilities of large language models (LLMs). As the ability of LLMs is constantly improving, they have been increasingly applied to…
From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
Zhexin Zhang, Junxiao Yang, Yida Lu +5
Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks. An important observation is that, while different types of jailbreak attacks can generate significantl…
AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models
Jiale Cheng, Yida Lu, Xiaotao Gu +6
Although Large Language Models (LLMs) are becoming increasingly powerful, they still exhibit significant but subtle weaknesses, such as mistakes in instruction-following or coding…
Learning Task Decomposition to Assist Humans in Competitive Programming
Jiaxin Wen, Ruiqi Zhong, Pei Ke +3
When using language models (LMs) to solve complex problems, humans might struggle to understand the LM-generated solutions and repair the flawed ones. To assist humans in repairing…
ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback
Zhenyu Hou, Yilin Niu, Zhengxiao Du +8
ChatGLM is a free-to-use AI service powered by the ChatGLM family of large language models (LLMs). In this paper, we present the ChatGLM-RLHF pipeline -- a reinforcement learning f…
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
Zhexin Zhang, Yida Lu, Jingyuan Ma +8
The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs'…
ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings
Hao Wang, Hao Li, Minlie Huang +1
The safety defense methods of Large language models(LLMs) stays limited because the dangerous prompts are manually curated to just few known attack types, which fails to keep pace…
Towards Efficient Exact Optimization of Language Model Alignment
Haozhe Ji, Cheng Lu, Yilin Niu +5
The alignment of language models with human preferences is vital for their application in real-world tasks. The problem is formulated as optimizing the model's policy to maximize t…