benchmark

human alignment (neural/behavioral)

benchmarkactiveprovisionalhuman-alignment-neural-behavioral--40703af2·1 events·first seen 20d ago

Aliases: human alignment (neural/behavioral)

Co-occurring entities

large language models fMRI eye-tracking Vision-Language Models multimodal pretraining

More like this (12)

human alignment benchmarks (perceptual similarity, gloss, robustness, shape-texture)human uncertainty alignment AI alignment anthropomorphism in AI Positive Alignment ALIGN human-in-the-loop pattern behavioral fine-tuning The Alignment Project misalignment generalization deliberative alignment post-training alignment

Recent events (1)

5arXiv · cs.CL·20d ago·source ↗

VLMs May Not Globally Enhance Human Alignment over LLMs During Natural Reading

This paper compares matched LLM and VLM pairs in a text-only setting to isolate the effect of multimodal training history on human-like language processing. Using whole-cortex fMRI and eye-tracking data from natural reading, the authors find that multimodal pretraining does not confer a uniform global advantage in human alignment. However, VLMs show selective advantages when sentences contain stronger visual semantic content, with converging evidence from both neural and behavioral measures. The findings suggest language-internal representations remain the primary driver of human text processing alignment.

Evaluation and Benchmarking Alignment and RLHF large language models human alignment (neural/behavioral)fMRI +4 more