Nowadays, developing reliable DeepResearch-style long-form report generation remains challenging, as training and evaluation lack verifiable reward signals. Accordingly, rubric-based evaluation has become a common practice. However, existing approaches either rely on coarse, pre-defined rubrics that lack sufficient granularity or depend on manually constructed query-specific rubrics that are costly and difficult to scale. In this paper, we propose a pipeline to train preference-grounded query-specific rubric generators tailored for DeepResearch report generation. We first construct a dataset of DeepResearch-style queries annotated with human preferences over paired reports, and train rubric generators via reinforcement learning with a hybrid reward combining preference consistency, format validity, and LLM-based rubric evaluation. We evaluate the resulting rubric generators in two stages. First, on a held-out human-preference test set, the learned rubrics discriminate preferred from rejected reports more effectively than generic, prompted, or SFT-trained rubric alternatives. Second, when used as reward signals to train DeepResearch systems, our rubric generators yield substantial performance gains under both a simple single-agent ReAct framework and a complex multi-agent workflow on the DeepResearch Bench. Our code and model are available at https://huggingface.co/fdu-lcz/rubric_generator.

Self-augmentation has received increasing research interest recently to improve named entity recognition (NER) performance in low-resource scenarios. Token substitution and mixup are two feasible heterogeneous self-augmentation techniques for NER that can achieve effective performance with certain specialized efforts. Noticeably, self-augmentation may introduce potentially noisy augmented data. Prior research has mainly resorted to heuristic rule-based constraints to reduce the noise for specific self-augmentation methods individually. In this paper, we revisit these two typical self-augmentation methods for NER, and propose a unified meta-reweighting strategy for them to achieve a natural integration. Our method is easily extensible, imposing little effort on a specific self-augmentation method. Experiments on different Chinese and English NER benchmarks show that our token substitution and mixup method, as well as their integration, can achieve effective performance improvement. Based on the meta-reweighting mechanism, we can enhance the advantages of the self-augmentation techniques without much extra effort.

Prompt-based paradigm has shown its competitive performance in many NLP tasks. However, its success heavily depends on prompt design, and the effectiveness varies upon the model and training data. In this paper, we propose a novel dual context-guided continuous prompt (DCCP) tuning method. To explore the rich contextual information in language structure and close the gap between discrete prompt tuning and continuous prompt tuning, DCCP introduces two auxiliary training objectives and constructs input in a pair-wise fashion. Experimental results demonstrate that our method is applicable to many NLP tasks, and can often outperform existing prompt tuning methods by a large margin in the few-shot setting.

Fine-grained Entity Typing (FET) has made great progress based on distant supervision but still suffers from label noise. Existing FET noise learning methods rely on prediction distributions in an instance-independent manner, which causes the problem of confirmation bias. In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems. FCLC first train a coarse backbone model as a feature extractor and noise estimator. Loss correction is then applied to each feature cluster, learning directly from the noisy labels. Experimental results on three public datasets show that FCLC achieves the best performance over existing competitive systems. Auxiliary experiments further demonstrate that FCLC is stable to hyperparameters and it does help mitigate confirmation bias. We also find that in the extreme case of no clean data, the FCLC framework still achieves competitive performance.