Franziska Weeber

Tristan Williams, Franziska Weeber, Sebastian Padó et al.

Large language models are increasingly used to represent human opinions, values, or beliefs, and their steerability towards these ideals is an active area of research. Existing work focuses predominantly on aligning marginal response distributions, treating each survey item independently. While essential, this may overlook deeper latent structures that characterise real populations and underpin cultural values theories. We propose a framework for evaluating the representativeness of aligned models through multivariate correlation patterns in addition to marginal distributions. We show the value of our evaluation scheme by comparing two model steering techniques (persona prompting and demographic fine-tuning) and evaluating them against human responses from the World Values Survey. While the demographically fine-tuned model better approximates marginal response distributions than persona prompting, both techniques fail to fully capture the gold standard correlation patterns. We conclude that representativeness is a distinct aspect of value alignment and an evaluation focused on marginals can mask structural failures, leading to overly optimistic conclusions about model capabilities.

Udo Schlegel, Franziska Weeber, Jian Lan et al.

Contrastive Language-Image Pre-training (CLIP) is a widely used multimodal model that aligns text and image representations through large-scale training. While it performs strongly on zero-shot and few-shot tasks, its robustness to linguistic variation, particularly paraphrasing, remains underexplored. Paraphrase robustness is essential for reliable deployment, especially in socially sensitive contexts where inconsistent representations can amplify demographic biases. In this paper, we introduce the Paraphrase Ranking Stability Metric (PRSM), a novel measure for quantifying CLIP's sensitivity to paraphrased queries. Using the Social Counterfactuals dataset, a benchmark designed to reveal social and demographic biases, we empirically assess CLIP's stability under paraphrastic variation, examine the interaction between paraphrase robustness and gender, and discuss implications for fairness and equitable deployment of multimodal systems. Our analysis reveals that robustness varies across paraphrasing strategies, with subtle yet consistent differences observed between male- and female-associated queries.

Franziska Weeber, Vera Neplenbroek, Jan Batzner et al.

Personalization of LLMs by sociodemographic subgroup often improves user experience, but can also introduce or amplify biases and unfair outcomes across groups. Prior work has employed so-called personas, sociodemographic user attributes conveyed to a model, to study bias in LLMs by relying on a single cue to prompt a persona, such as user names or explicit attribute mentions. This disregards LLM sensitivity to prompt variations (robustness) and the rarity of some cues in real interactions (external validity). We compare six commonly used persona cues across seven open and proprietary LLMs on four writing and advice tasks. While cues are overall highly correlated, they produce substantial variance in responses across personas. We therefore caution against claims from a single persona cue and recommend future personalization research to evaluate multiple externally valid cues.

Michelle Barbosa, Sebastian Padó, Franziska Weeber

Socio-cultural stereotypical bias is an important consideration in the development and deployment of NLP systems. It is however often considered only at the national level, despite rich subnational socio-cultural structures. We present AmchiBias, the first benchmark for measuring socio-cultural stereotypical bias for the Indian state of Goa with its unique historically multicultural setting. It covers various Goan identity groups and comprises 313 minimal pairs across eight sociodemographic dimensions in both English and Devanagari Konkani. We then evaluate stereotypical bias in five multilingual encoder models on this benchmark. We find near-chance scores in Konkani, reflecting language incompetence for general multilingual models and a lack of Goan cultural competence for Indian language models. Queried in English, models with a stronger Indian language coverage show higher bias for pan-Indian groups than hyperlocal Goan groups. This suggests the English signal reflects pan-Indian pretraining associations rather than genuine Goan cultural knowledge. Our findings highlight a critical gap in low-resource multilingual NLP evaluation for hyperlocal community identities.

Franziska Weeber, Felix Hamborg, Karsten Donnay et al.

Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality, annotated datasets with only a few manual annotations, thus strongly reducing annotation cost and effort. For this purpose, we combine an active learning (AL) approach with a pre-trained language model to semi-automatically identify annotation categories in the given text documents. To highlight our research direction's potential, we evaluate the approach on the task of identifying frames in news articles. Our preliminary results show that employing AL strongly reduces the number of annotations for correct classification of even these complex and subtle frames. On the framing dataset, the AL approach needs only 16.3\% of the annotations to reach the same performance as a model trained on the full dataset.