The paper examines how large language models (LLMs) can be biased by irrelevant social contexts when evaluating teachers, using a large U.S. classroom transcript dataset. It shows that spurious contexts can shift model ratings by up to 1.48 points on a 7‑point scale and that standard mitigation methods like SFT and DPO are insufficient. The authors introduce Debiasing‑DPO, a method that combines contrastive reasoning‑augmented DPO with SFT, which reduces bias by 84% and improves predictive accuracy by 52% on Llama and Qwen Instruct models.
arXiv:2606. 01584v1 Announce Type: cross Abstract: Conversational tutoring agents have been shown to improve learning engagement and student outcomes, and large language models (LLMs) are increasingly used in these systems to provide scalable, personalized feedback.
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.
arXiv:2602.02219v3 Announce Type: replace Abstract: Large language models are widely employed as evaluators, a paradigm commonly referred to as LLM-as-a-judge. Prior research has predominantly examin...
arXiv:2606. 06546v1 Announce Type: new Abstract: Evaluating large language models (LLMs) for education requires measuring how models teach, not only what they know.
arXiv:2608. 03632v1 Announce Type: new Abstract: On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals.
arXiv:2608. 14161v1 Announce Type: new Abstract: LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in high-stakes applications.
arXiv:2607. 10805v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs).
arXiv:2608.31079v1 Announce Type: new Abstract: Sycophantic agreement refers to a behavior in which language models excessively affirm the user, often at the cost of factual accuracy. Although sycoph...
arXiv:2610.09384v1 Announce Type: cross Abstract: Language models are routinely fine-tuned under a fixed context, such as a generic system prompt, persona or domain-specific instruction, yet the lear...
arXiv:2610.08559v1 Announce Type: cross Abstract: Activation steering has gained popularity as a lightweight inference-time debiasing technique for large language models. However, prior work reports...
The paper presents GRASP, a method for unsupervised detection and removal of spurious correlations that arise during fine‑tuning of pretrained language models. By identifying latent factors from LoRA fine‑tune weights and projecting gradients to prevent new reliance on them, GRASP preserves genuine task signals while mitigating bias. Experiments on three tasks—misaligned code generation, medical advice, and political bias—show that GRASP reduces misalignment and drift more effectively than existing baselines while maintaining task performance.
arXiv:2604. 07102v2 Announce Type: replace-cross Abstract: Activation-based steering enables inference-time personalization of large language models, but its effects in educational applications are not well understood.