arXiv:2604.20677v3 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and bias, particularly when...
The paper introduces a reference‑based bias detection method that audits hidden‑state representations of language models by encoding sentences as similarities to a fixed set of anchor sentences. This relative representation allows comparison across model variants, such as before and after fine‑tuning, and yields a metric called Representational Bias Shift (ΔB). ΔB correlates strongly with output‑level bias changes, can detect bias‑increasing checkpoints with high ROC AUC, and is computationally efficient, requiring only a few minutes and far less compute than traditional benchmarks.
The paper demonstrates that large language model (LLM) evaluators, whether reward‑model based or prompted LLM‑as‑a‑Judge, exhibit significant language bias in multilingual settings. Experiments with semantically identical instruction‑response pairs across 23 languages reveal that lower‑resource languages receive higher scores, a bias that persists across eight open‑weight evaluators and is not detectable by standard pairwise accuracy metrics. The authors link the bias to model uncertainty and language identity, showing it cannot be explained by content difficulty alone.
arXiv:2607. 28801v1 Announce Type: cross Abstract: Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial variation in the demands of individual samples.
arXiv:2509. 16462v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used in high-stakes decision-making systems, where biased predictions can reinforce social and economic disparities.
arXiv:2605. 23055v2 Announce Type: replace-cross Abstract: Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results.
arXiv:2606. 10632v1 Announce Type: cross Abstract: Lipschitz-style individual fairness formalizes the idea that semantically similar examples should receive similar predictions, but its evaluation in multi-task learning (MTL) can be confounded by method-induced representation scales.
arXiv:2503.05684v2 Announce Type: replace-cross Abstract: Pre-trained foundation models can be efficiently adapted for specific tasks using Low-Rank Adaptation (LoRA), but the fairness properties of...
arXiv:2602. 04306v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial.
arXiv:2601.03087v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit systematic biases across demographic groups. Auditing is proposed as an accountability tool for black-box LLM...
arXiv:2606. 03650v1 Announce Type: cross Abstract: Choosing or ranking language models for a specific application is hardest when no task-specific labeled data exists, and standard public benchmarks cannot be trusted, their items having likely leaked into pretraining, so scores reflect memorization rather than fitness.
arXiv:2409.00696v4 Announce Type: replace-cross Abstract: Rating-based human evaluation has become an essential tool to accurately evaluate the impressive performance of large language models (LLMs)....