Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities such as text coherence and task accuracy. And Prompt-based debiasing methods, only effective for predefined trigger words, fail to address deeply embedded stereotypical associations in model parameters. In this paper, we propose BiasUnlearn, a novel model debiasing framework which achieves targeted debiasing via dual-pathway unlearning mechanisms coordinating stereotype forgetting with anti-stereotype retention, while preventing bias polarity reversal through adversarial forget set and dynamic dataset swapping. We conducted extensive experiments with multiple language models across various evaluation benchmarks. The results show that BiasUnlearn outperforms existing methods in mitigating bias in language models while retaining language modeling capabilities. Further experiments reveal that debiasing weights are transferable across model variants, confirming that bias representations become entrenched during pre-training and persist through fine-tuning phases.

Retrieval-augmented generation (RAG) effectively mitigates hallucinations in large language models (LLMs) by filling knowledge gaps with retrieved external information. Most existing studies primarily retrieve knowledge documents based on semantic similarity to assist in answering questions but ignore the fine-grained necessary information within documents. In this paper, we propose a novel fine-grained knowledge enhancement method (FKE) for RAG, where fine-grained knowledge primarily includes sentence-level information easily overlooked in the document-based retrieval process. Concretely, we create a disentangled Chain-of-Thought prompting procedure to retrieve fine-grained knowledge from the external knowledge corpus. Then we develop a decoding enhancement strategy to constrain the document-based decoding process using fine-grained knowledge, thereby facilitating more accurate generated answers. Given an existing RAG pipeline, our method could be applied in a plug-and-play manner to enhance its performance with no additional modules or training process. Extensive experiments verify the effectiveness and generality of our method.