Conversational stance detection, which aims to identify users’ attitudes in conversation threads, has attracted increasing attention in recent years. Yet, mainstream LLM-based approaches remain prone to biases caused by spurious correlations. Existing debiasing methods either rely on indiscriminate multi-step prompting, which can induce unnecessary reasoning and overthinking, or require expensive fine-tuning on curated data. To address these challenges, we propose ExpCSD, an experience-based debiasing framework grounded in latent thinking paths that follows a debias-only-when-needed principle. ExpCSD first assesses whether an LLM’s latent thinking path is biased and selectively retrieves and injects historically similar debiasing experiences only when necessary, without updating model parameters. Experiments on public benchmarks show that ExpCSD outperforms strong baselines in stance detection accuracy while avoiding overthinking and costly fine-tuning.

Semi-supervised entity alignment (EA) is a practical and challenging task because of the lack of adequate labeled mappings as training data. Most works address this problem by generating pseudo mappings for unlabeled entities. However, they either suffer from the erroneous (noisy) pseudo mappings or largely ignore the uncertainty of pseudo mappings. In this paper, we propose a novel semi-supervised EA method, termed as MixTEA, which guides the model learning with an end-to-end mixture teaching of manually labeled mappings and probabilistic pseudo mappings. We firstly train a student model using few labeled mappings as standard. More importantly, in pseudo mapping learning, we propose a bi-directional voting (BDV) strategy that fuses the alignment decisions in different directions to estimate the uncertainty via the joint matching confidence score. Meanwhile, we also design a matching diversity-based rectification (MDR) module to adjust the pseudo mapping learning, thus reducing the negative influence of noisy mappings. Extensive results on benchmark datasets as well as further analyses demonstrate the superiority and the effectiveness of our proposed method.