Showing 2025Show all
3 papers · 1 filter
cs.CL2025
From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens
Hala Sheta, Eric Huang, Shuyu Wu +9
We introduce VLM-Lens, a toolkit designed to enable systematic benchmarking, analysis, and interpretation of vision-language models (VLMs) by supporting the extraction of intermedi…
cs.CL2025
The Mechanistic Emergence of Symbol Grounding in Language Models
Shuyu Wu, Ziqiao Ma, Xiaoxi Luo +4
Symbol grounding (Harnad, 1990) describes how symbols such as words acquire their meanings by connecting to real-world sensorimotor experiences. Recent work has shown preliminary e…
cs.CL2025
Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce
Haojin Wang, Zining Zhu, Freda Shi
Autoregressive neural language models (LMs) generate a probability distribution over tokens at each time step given a prompt. In this work, we attempt to systematically understand…