Tag
A viral tweet highlights a claimed advance called RL with Neural Feedback (RLNF), where AI models are trained to align with human preferences using direct brain signals, demonstrated via a face image that transforms into a more attractive version in real time as the subject views it.
Introducing RL with Neural Feedback (RLNF), a method claiming reliable training of AI models to align with human preferences using only brain signals, demonstrated via a face image that self-transforms into a more attractive version for the viewer.
Introduces Rushes, a large-scale dataset of human engagement preferences in AI-generated branching narratives, revealing that current LLMs like GPT-5 fail to outperform simple baselines in predicting user choices, highlighting the need for personalized alignment.
A new study tests LLMs across 28 real-world studies and finds they match human majority only 53% of the time, no better than random, challenging the trend of using LLMs to replace human feedback.
This position paper argues that large language models should learn from personalized rather than aggregated human preferences, highlighting theoretical limitations from social choice theory and practical issues from demographic diversity. It proposes bounded personalization frameworks that respect individual autonomy while maintaining universal safety constraints.
SenseJudge is a human-centric framework for customizable LLM judging that adapts to diverse user preferences, outperforming existing methods. It also introduces SenseBench, a benchmark derived from real-world multi-turn interactions.
Brian Christian announces his official full-time researcher position at CHAI Berkeley after nearly a decade of affiliation, building on his PhD work on AI representation of human preferences.
This paper introduces 3DCodeBench, a benchmark for evaluating vision-language models on procedural 3D modeling via code, and 3DCodeArena, a ranking platform based on pairwise human preferences.
HP-Edit introduces a post-training framework that aligns diffusion-based image editing models with human preferences via RLHF, using a new 50K real-world dataset and an automatic VLM-based evaluator.