Related papers: HEARTS: A Holistic Framework for Explainable, Sust…

Correct answers do not necessarily reflect cultural understanding. We introduce CRaFT, an explanation-based multilingual evaluation framework designed to assess how large language models (LLMs) reason across cultural contexts. Rather than…

Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned their faithfulness, as they may not accurately reflect the…

With the rapid advancement of Multimodal Large Language Models (MLLMs), they have demonstrated exceptional capabilities across a variety of vision-language tasks. However, current evaluation benchmarks predominantly focus on objective…

Recent advances in generative AI have enabled visual content creation through text-to-image (T2I) generation. However, despite their creative potential, T2I models often replicate and amplify societal stereotypes -- particularly those…

In explainable artificial intelligence (XAI) research, the predominant focus has been on interpreting models for experts and practitioners. Model agnostic and local explanation approaches are deemed interpretable and sufficient in many…

Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social…

Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming and low in coverage, while large language models (LLMs) often…

Discrimination has been shown in many machine learning applications, which calls for sufficient fairness testing before their deployment in ethic-relevant domains such as face recognition, medical diagnosis and criminal sentence. Existing…

Warning: This paper contains several contents that may be toxic, harmful, or offensive. In the last few years, text-to-image generative models have gained remarkable success in generating images with unprecedented quality accompanied by a…

We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the discriminative cues present in language, such as semantic or stylistic structure. Each…

Data visualizations like charts are fundamental tools for quantitative analysis and decision-making across fields, requiring accurate interpretation and mathematical reasoning. The emergence of Multimodal Large Language Models (MLLMs)…

Representational harms in language technologies often occur in short spans within otherwise neutral text, where phrases may simultaneously convey generalizations, unfairness, or stereotypes. Framing bias detection as sentence-level…

Genuine spatial reasoning relies on the capacity to construct and manipulate coherent internal spatial representations, often conceptualized as mental models, rather than merely processing surface linguistic associations. While large…

Empathy serves as a cornerstone in enabling prosocial behaviors, and can be evoked through sharing of personal experiences in stories. While empathy is influenced by narrative content, intuitively, people respond to the way a story is told…

Empathy indicates an individual's ability to understand others. Over the past few years, empathy has drawn attention from various disciplines, including but not limited to Affective Computing, Cognitive Science, and Psychology. Detecting…

Structured prediction requires models to generate ontology-constrained labels, grounded evidence, and valid structure under ambiguity, label skew, and heterogeneous group difficulty. We present a two-part framework for controllable…

Optimization of offensive content moderation models for different types of hateful messages is typically achieved through continued pre-training or fine-tuning on new hate speech benchmarks. However, existing benchmarks mainly address…

As Large Language Models for Code (LM4Code) become integral to software engineering, establishing trust in their output becomes critical. However, standard accuracy metrics obscure the underlying reasoning of generative models, offering…

This research introduces the Multilevel Embedding Association Test (ML-EAT), a method designed for interpretable and transparent measurement of intrinsic bias in language technologies. The ML-EAT addresses issues of ambiguity and difficulty…

Large language models (LLMs) are widely deployed for open-ended communication, yet most bias evaluations still rely on English, classification-style tasks. We introduce \corpusname, a new multilingual, debate-style benchmark designed to…