Dingling Xu, Ruobing Wang, Qingfei Zhao, Yukun Yan, Zhichun Wang, Daren Zha, Shi Yu, Zhenghao Liu, Shuo Wang, Xu Han, Maosong Sun. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Live commerce platforms frequently employ algorithmic recommendations and time-limited promotions to trigger impulsive purchases, challenging rational consumer decision-making. While existing research has identified manipulative design patterns in live commerce, significant gaps remain in understanding consumer psychological motivations and developing counter-persuasion interventions. We conducted a multi-stage formative study involving surveys (N = 116), interviews (N = 21), and co-design workshops (N = 16) to explore user preferences for rational consumption support systems. Informed by these insights, we designed BuyMate, which provides gentle, real-time rational interventions through product comparison and persuasive speech reframing. A user evaluation (N = 35) demonstrates that the system effectively reduces impulsive purchases, enhances decision autonomy, and promotes sustainable consumption. This work contributes an AI-driven counter-persuasion approach, identifies user-centered principles for adaptive interventions, and offers practical guidance for responsible AI in digital commerce.

Long-Context Question Answering (LCQA), a challenging task, aims to reason over longcontext documents to yield accurate answers to questions.Existing long-context Large Language Models (LLMs) for LCQA often struggle with the "lost in the middle" issue.Retrieval-Augmented Generation (RAG) mitigates this issue by providing external factual evidence.However, its chunking strategy disrupts the global long-context information, and its low-quality retrieval in long contexts hinders LLMs from identifying effective factual details due to substantial noise.To this end, we propose LongRAG, a general, dual-perspective, and robust LLM-based RAG system paradigm for LCQA to enhance RAG's understanding of complex long-context knowledge (i.e., global information and factual details).We design LongRAG as a plug-and-play paradigm, facilitating adaptation to various domains and LLMs.Extensive experiments on three multihop datasets demonstrate that LongRAG significantly outperforms long-context LLMs (up by 6.94%), advanced RAG (up by 6.16%), and Vanilla RAG (up by 17.25%).Furthermore, we conduct quantitative ablation studies and multidimensional analyses, highlighting the effectiveness of the system's components and finetuning strategies.Data and code are available at https://github.com/QingFei1/LongRAG.

With the rapid proliferation of scientific literature, versatile academic knowledge services increasingly rely on comprehensive academic graph mining. Despite the availability of public academic graphs, benchmarks, and datasets, these resources often fall short in multi-aspect and fine-grained annotations, are constrained to specific task types and domains, or lack underlying real academic graphs. In this paper, we present OAG-Bench, a comprehensive, multi-aspect, and fine-grained human-curated benchmark based on the Open Academic Graph (OAG). OAG-Bench covers 10 tasks, 20 datasets, 70+ baselines, and 120+ experimental results to date. We propose new data annotation strategies for certain tasks and offer a suite of data pre-processing codes, algorithm implementations, and standardized evaluation protocols to facilitate academic graph mining. Extensive experiments reveal that even advanced algorithms like large language models (LLMs) encounter difficulties in addressing key challenges in certain tasks, such as paper source tracing and scholar profiling. We also introduce the Open Academic Graph Challenge (OAG-Challenge) to encourage community input and sharing. We envisage that OAG-Bench can serve as a common ground for the community to evaluate and compare algorithms in academic graph mining, thereby accelerating algorithm development and advancement in this field. OAG-Bench is accessible at https://www.aminer.cn/data/.

Multimodal Conversational Emotion recognition (MMCER) aims to detect the muti-emotion label for each utterance from heterogeneous visual, text and audio modalities. In this paper, we focus on applying multi-modal graph data structures to conversational emotion recognition and use a novel and efficient graph—MMDCGs to better integrate multi-modal contextual information into conversations. MMDCG provides a new way of encoding intrinsic structural connectivity. Besides, inspired by time series analysis, we set a rolling time window as the receptive field, which can reduce the interference of remote information on the current utterances detection and achieve the purpose of data enhancement. We innovatively ensemble such graph structures with transformers, named rolling-windows MMDCGs (RW-MMDCG). Comprehensive experiments are performed on two representative multi-modal datasets, IEMOCAP and MELD, and we compare them with existing baselines, demonstrating the great advantages and effectiveness of RW-MMDCG.