The paper audits six LLMs across four languages, finding that their gender stereotyping is significantly wider than human baselines and that cross-lingual translation fundamentally alters the nature o…

The paper demonstrates that using English prompts causes large language models to prioritize globally dominant narratives over local cultural knowledge, even when local evidence is provided.

The paper introduces BiAxisAudit, a novel framework that evaluates LLM bias by analyzing bias scores across multiple prompt formats and within the internal inconsistency of model responses, revealing…

The paper introduces a diagnostic framework to decompose multilingual LLM performance variance, showing that language identity and model-benchmark interactions are key drivers of performance gaps.

The paper introduces CultureForest, a new benchmark for evaluating Cultural Norm Grounded Reasoning in LLMs, demonstrating that models struggle to apply their cultural knowledge effectively in realist…

The paper develops a theoretically grounded framework for evaluating multilingual LLMs in Social Sciences and Humanities, moving beyond traditional NLP benchmarks to assess interpretive validity and c…

The paper introduces the Triangulated Preference Shift score, an automated, curation-free metric to quantify systematic lexical biases introduced into Large Language Models during the preference-learn…

This paper introduces a Hybrid Mixture-of-Experts (HybridMoE) framework and a specialized corpus (Varnika) to significantly improve language models' ability to understand and retain figurative, cultur…

This study evaluates LLMs in conversational tutoring to identify high-confidence social biases, finding that state-of-the-art models are often overconfident in their incorrect assessments of stereotyp…

The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from…

The paper proposes an Interpretive Audit Pipeline to evaluate LLMs for public comment analysis, arguing that measuring inter-model disagreement is crucial because standard accuracy metrics fail to det…

The paper proposes a neuron-level intervention method to identify and control gender-specific representations (feminine, masculine, and gender-neutral) within large language models, demonstrating prec…

This paper proposes a domain-specialized large language model, PoetryQwen, for precise translation and emotional understanding of classical poetry.

The paper introduces PRAIB, a benchmark that demonstrates that LLM-generated peer reviews, while often verbose, systematically diverge from human norms by being less variable, positively biased, and f…

This paper analyzes the multilinguality of LLMs by examining their structural properties, finding that low-resource languages are structurally more distinct from English than high-resource languages,…

BiasEdit introduces a training-free framework that automatically detects and edits unknown social biases in web-sourced image datasets to construct a debiased dataset for fair visual classification.

The paper demonstrates that the AI-like style introduced by post-training alignment can be measured, localized, and causally removed using a novel ablation technique called PASTA.

The paper introduces UA-Legal-Bench, a comprehensive Ukrainian legal reasoning benchmark built from a massive judicial corpus, demonstrating that LLM performance is highly task-dependent and that simp…