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.

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.

Text-based knowledge graph completion (KGC) methods utilize pre-trained language models for triple encoding and further fine-tune the model to achieve completion. Despite their excellent performance, they neglect the knowledge context in inferring process. Intuitively, knowledge contexts, which refer to the neighboring triples around the target triples, are important information for triple inferring, since they provide additional detailed information about the entities. To this end, we propose a novel framework named KnowC, which models the knowledge context as additional prompts with pre-trained language models for knowledge graph completion. Given the substantial number of neighbors typically associated with entities, along with the constrained input token capacity of language models, we further devise several strategies to sample the neighbors. We conduct extensive experiments on common datasets FB15k-237, WN18RR and Wikidata5M, experiments show that KnowC achieves state-of-the-art performance.

Complex KBQA leverages the knowledge base (KB) to answer complex natural questions involving complicated semantics like multi-hop reasoning. Existing methods involve a question decomposition process, i.e., breaking a complex question into several simpler sub-questions, to assist obtaining logical forms for querying the KB. However, existing question decomposition process derives all sub-questions directly according to the original question, resulting in limitations when one sub-question relies on the answer from a previous one. In this work, we propose Chain-of-Question, a progressive question decomposition approach to address complex KBQA challenges. First, inspired by chain-of-thought, we design a prompt to guide LLM to sequentially decompose multiple semantically clear sub-questions and provide corresponding reference answers, where each step of the decomposition relies on the previous results. Next, we utilize the decomposition result to select relevant patterns (relation-entity pairs) as accurate and faithful auxiliary information for the following logical form generation. Finally, we jointly perform logical form generation and answer prediction, utilizing the predicted answer to supplement non-executable logical forms. Experimental results demonstrate that our method achieves state-of-the-art performance on multiple datasets.

Recently, tremendous strides have been made to align the generation of Large Language Models (LLMs) with human values to mitigate toxic or unhelpful content. Leveraging Reinforcement Learning from Human Feedback (RLHF) proves effective and is widely adopted by researchers. However, implementing RLHF is complex, and its sensitivity to hyperparameters renders achieving stable performance and scalability challenging. Furthermore, prevailing approaches to preference alignment primarily concentrate on pairwise comparisons, with limited exploration into multi-response scenarios, thereby overlooking the potential richness within the candidate pool. For the above reasons, we propose a new approach: Listwise Reward Enhancement for Preference Alignment (LIRE), a gradient-based reward optimization approach that incorporates the offline rewards of multiple responses into a streamlined listwise framework, thus eliminating the need for online sampling during training. LIRE is straightforward to implement, requiring minimal parameter tuning, and seamlessly aligns with the pairwise paradigm while naturally extending to multi-response scenarios. Moreover, we introduce a self-enhancement algorithm aimed at iteratively refining the reward during training. Our experiments demonstrate that LIRE consistently outperforms existing methods across several benchmarks on dialogue and summarization tasks, with good transferability to out-of-distribution data, assessed using proxy reward models and human annotators.