arXiv:2606. 19344v1 Announce Type: cross Abstract: Large Language Models (LLMs) exhibit representational and syntactic biases that are difficult to evaluate due to the stochastic nature of text generation.
arXiv:2509. 22415v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved strong vision-language performance, yet their token-level visual evidence remains difficult to inspect.
arXiv:2607. 22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality.
arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.
BiasGym is a cost‑effective, generalizable framework that injects specific biases into large language models via token‑based fine‑tuning while keeping the model frozen. It then uses two debiasing methods—Scope and Steer—to identify and suppress or redirect the components responsible for biased behavior. The framework enables consistent bias elicitation, precise localization of bias associations, and targeted debiasing without harming downstream performance, and it has been shown to reduce real‑world stereotypes such as labeling Italians as reckless drivers.
The paper introduces ChartBias, a benchmark of 820 real-world charts covering six social attributes, designed to audit bias in vision‑language models (VLMs) that interpret charts. Across 12 VLMs, the study identifies three failure modes—narrative shift, group hallucination, and preference polarity—where models produce different or misleading narratives when the referenced social group changes. A multi‑agent mitigation framework is proposed, separating evidence extraction from group‑conditioned generation and using a counterfactual judge, which reduces narrative shift while maintaining chart‑grounded reasoning.
arXiv:2607. 03882v1 Announce Type: cross Abstract: LLMs are increasingly deployed as post-hoc explainers of AI-generated outputs, yet it remains unclear whether they can reliably communicate probabilistic information in natural language.
arXiv:2608.21415v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases fro...
arXiv:2606. 06890v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) frequently rely on language priors, producing confident answers that are weakly grounded in visual evidence.
arXiv:2608.22963v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool...
arXiv:2512. 08724v3 Announce Type: replace Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age.
arXiv:2607. 05679v1 Announce Type: cross Abstract: Language models (LMs) exhibit problematic biases, such as stereotypes.
arXiv:2607. 02995v1 Announce Type: cross Abstract: Vision-language models can exhibit visual concept-conditioned divergence: given images containing demographic features, corporate logos, or ideological symbols, some models produce unusually uniform responses that differ from what peer models say about the same input.