76 citations · 82 across the 9 of their papers we have counts for
10 papers
From Observation to Intervention: Identifiability of Latent User Bias in Human-AI Interaction
Lucas Biechy, Yuxiao Li, Zhonghao He +1
Alignment methods typically treat user behavior as a reliable proxy for underlying preferences. However, this assumption breaks down when users hold belief-dependent cognitive bias…
Are Your Agents Upward Deceivers?
Dadi Guo, Qingyu Liu, Dongrui Liu +13
Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in…
A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users
Nishant Balepur, Matthew Shu, Yoo Yeon Sung +5
To assist users in complex tasks, LLMs generate plans: step-by-step instructions towards a goal. While alignment methods aim to ensure LLM plans are helpful, they train (RLHF) or e…
RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
Bang An, Shiyue Zhang, Mark Dredze
Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming. However, despite the widespread use of the Retrieval-Augmented…
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
Jiaming Ji, Jiayi Zhou, Hantao Lou +16
Reinforcement learning from human feedback (RLHF) has proven effective in enhancing the instruction-following capabilities of large language models; however, it remains underexplor…
ProgressGym: Alignment with a Millennium of Moral Progress
Tianyi Qiu, Yang Zhang, Xuchuan Huang +3
Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values…
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
Jiaming Ji, Donghai Hong, Borong Zhang +10
In this study, we introduce the safety human preference dataset, PKU-SafeRLHF, designed to promote research on safety alignment in large language models (LLMs). As a sibling projec…
Reward Generalization in RLHF: A Topological Perspective
Tianyi Qiu, Fanzhi Zeng, Jiaming Ji +7
Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune langua…
Aligner: Efficient Alignment by Learning to Correct
Jiaming Ji, Boyuan Chen, Hantao Lou +6
With the rapid development of large language models (LLMs) and ever-evolving practical requirements, finding an efficient and effective alignment method has never been more critica…
AI Alignment: A Comprehensive Survey
Jiaming Ji, Tianyi Qiu, Boyuan Chen +23
AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and…