4 papers
PowerBench: Measuring Language Model Bias in Power-shifting Requests
Nicolas Martorell, Wendy Brau, Gonzalo A. Heredia +3
Language models increasingly assist people with power-related requests, so systematic differences in whom they help could shift the distribution of power at scale, or be exploited…
Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers
Carmen Quiles-Ramírez, Leticia L. Rodríguez, Nicolás Martorell +1
In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples. Yet, how these models use the provided context remains o…
Don't Ask: Understanding What Numeric Self-Reports Measure in Language Models
Nicolas Martorell, Bruno Bianchi
Language models are often asked to rate their internal states with a number, but it is unclear how reliable this measure is. We train probes for four affective concepts (wellbeing,…
From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task
Nicolas Martorell
Understanding how large language models (LLMs) represent and reason about spatial information is crucial for building robust agentic systems that can navigate real and simulated en…