Boyan Duan, Xiao Liang, Shuai Lu, Yaoxiang Wang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Mao Yang, Weizhu Chen, Yeyun Gong. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

The integration of service robots is reshaping hospitality, yet the mechanisms through which robotic and human service providers influence customer satisfaction remain underexplored. Drawing on dual-process and role theories, this study examines how service provider roles (robots vs. humans) affect satisfaction via utilitarian and hedonic values, moderated by customer social needs and restaurant status. Three experiments reveal that robots enhance utilitarian value, while humans foster hedonic value, each boosting satisfaction through different pathways. Customers with high social needs prefer human service for its experiential benefits, whereas those with low social needs favour robotic efficiency. In fine-dining contexts, human service more effectively elevates satisfaction via hedonic value, an effect absent in casual or quick-service settings. These findings advance theoretical understanding of rational and emotional mechanisms in service evaluation and offer practical guidance for aligning automation strategies with customer traits and restaurant positioning.

Existing methods for code generation use code snippets as seed data, restricting the complexity and diversity of the synthesized data. In this paper, we introduce a novel feature tree-based synthesis framework, which revolves around hierarchical code features derived from high-level abstractions of code. The feature tree is constructed from raw data and refined iteratively to increase the quantity and diversity of the extracted features, which captures and recognizes more complex patterns and relationships within the code. By adjusting the depth and breadth of the sampled subtrees, our framework provides precise control over the complexity of the generated code, enabling functionalities that range from function-level operations to multi-file scenarios. We fine-tuned widely-used base models to obtain EpiCoder series, achieving state-of-the-art performance on multiple benchmarks at both the function and file levels. In particular, empirical evidence indicates that our approach shows significant potential in the synthesizing of repository-level code data. Our code and data are publicly available.

Despite the impressive few-shot performance of in-context learning (ICL), it remains a common practice to randomly select examples to serve as the context.In this paper, we advocate self-adaptive in-context learning, a new principle for ICL, in which the self-adaption mechanism is introduced to help each input find an in-context example organization (i.e., selection and permutation) that can derive the correct output, thus maximizing performance.To validate the effectiveness of self-adaptive ICL, we propose a general select-then-rank framework and a set of novel selection and ranking algorithms.Upon extensive evaluation on eight different NLP datasets, our self-adaptive ICL method achieves a 40% relative improvement over the common practice setting.Further analysis reveals the great potential of selfadaptive ICL as a promising method to close the gap between ICL and finetuning.Our code will be released to facilitate future research.

As commonly-used methods for debiasing natural language understanding (NLU) models, dataset refinement approaches heavily rely on manual data analysis, and thus maybe unable to cover all the potential biased features.In this paper, we propose IBADR, an Iterative Bias-Aware Dataset Refinement framework, which debiases NLU models without predefining biased features.We maintain an iteratively expanded sample pool.Specifically, at each iteration, we first train a shallow model to quantify the bias degree of samples in the pool.Then, we pair each sample with a bias indicator representing its bias degree, and use these extended samples to train a sample generator.In this way, this generator can effectively learn the correspondence relationship between bias indicators and samples.Furthermore, we employ the generator to produce pseudo samples with fewer biased features by feeding specific bias indicators.Finally, we incorporate the generated pseudo samples into the pool.Experimental results and in-depth analyses on two NLU tasks show that IBADR not only significantly outperforms existing dataset refinement approaches, achieving SOTA, but also is compatible with model-centric methods. 1