Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge
LLM-as-a-Judge employs large language models (LLMs), such as GPT-4, to evaluate the quality of LLM-generated responses, gaining popularity for its cost-effectiveness and strong alignment with human evaluations. However, training proxy judge models using evaluation data generated by powerful teacher models introduces a critical yet previously overlooked issue: teacher preference bias, where the proxy judge model learns a biased preference for responses from the teacher model. To tackle this problem, we propose a novel setting that incorporates an additional assistant model, which is not biased toward the teacher model's responses, to complement the training data. Building on this setup, we introduce AGDe-Judge, a three-stage framework designed to debias from both the labels and feedbacks in the training data. Extensive experiments demonstrate that AGDe-Judge effectively reduces teacher preference bias while maintaining strong performance across six evaluation benchmarks. Code is available at https://github.com/Liuz233/AGDe-Judge.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Pareto-Guided Teacher Alignment for Fair Personalized Text Generation
Personalized persuasive text generation can improve relevance and engagement, but demographic conditioning may also introduce unequal framing across groups. We study fairness mitigation in personalized generation as a co…
Text GenerationDensely Guided Knowledge Distillation using Multiple Teacher Assistants
With the success of deep neural networks, knowledge distillation which guides the learning of a small student network from a large teacher network is being actively studied for model compression and transfer learning. Ho…
Knowledge DistillationModel CompressionTransfer LearningWho Gets Cited? Gender- and Majority-Bias in LLM-Driven Reference Selection
Large language models (LLMs) are rapidly being adopted as research assistants, particularly for literature review and reference recommendation, yet little is known about whether they introduce demographic bias into citat…
Mitigating LLM biases toward spurious social contexts using direct preference optimization
LLMs are increasingly used for high-stakes decision-making, yet their sensitivity to spurious contextual information can introduce harmful biases. This is a critical concern when models are deployed for tasks like evalua…
User-Assistant Bias in LLMs
Modern large language models (LLMs) are typically trained and deployed using structured role tags (e.g. system, user, assistant, tool) that explicitly mark the source of each piece of context. While these tags are essent…
Instruction Following