Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Ye Qi, Zhicheng Dou. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations.Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still face several limitations: additional deployment costs of separate retrievers, redundant input tokens from retrieved text chunks, and the lack of joint optimization of retrieval and generation.To address these issues, we propose RetroLLM, a unified framework that integrates retrieval and generation into a single, auto-regressive process, enabling LLMs to directly generate fine-grained evidence from the corpus with constrained decoding.Moreover, to mitigate false pruning in the process of constrained evidence generation, we introduce (1) hierarchical FM-Index constraints, which generate corpus-constrained clues to identify a subset of relevant documents before evidence generation, reducing irrelevant decoding space; and (2) a forward-looking constrained decoding strategy, which considers the relevance of future sequences to improve evidence accuracy.Extensive experiments on five open-domain QA datasets demonstrate RetroLLM's superior performance across both in-domain and out-ofdomain tasks.The code is available at https: //github.com/sunnynexus/RetroLLM.

Air writing technology enhances text input for IoT, VR, and AR devices, offering a spatially flexible alternative to physical keyboards. Addressing the demand for such innovation, this paper presents MagicWrite, a novel system utilizing acoustic-based 1D tracking, which is suitable for mobile devices with existing speaker and microphone infrastructure. Compared to 2D or 3D tracking of the finger, 1D tracking eliminates the need for multiple microphones and/or speakers and is more universally applicable. However, challenges emerge when using 1D tracking for recognizing handwritten letters due to trajectory loss and inter-user writing variability. To address this, we develop a general conversion technique that transforms image-based text datasets (e.g., MNIST) into 1D tracking trajectory data, generating artificial datasets of tracking traces (referred to asTrackMNISTs) to bolster system robustness and scalability. These tracking datasets facilitate the creation of personalized user databases that align with individual writing habits. Combined with a kNN classifier, our proposed MagicWrite ensures high accuracy and robustness in text input recognition while simultaneously reducing computational load and energy consumption. Extensive experiments validate that our proposed MagicWrite achieves exceptional classification accuracy for unseen users and inputs in five languages, marking it as a robust solution for air writing.

5G and Industrial Internet are bringing a variety of applications with on-time and reliable demands. Cyclic queuing and forwarding (CQF), a well-known mechanism defined by IEEE 802.1 Qch in Time Sensitive Network (TSN), achieves deterministic end-to-end latency and jitter without complex gating calculations. However, most of the current work ignores the prevalence of hybrid networks with different link rates, resulting in low bandwidth utilization and high latency for single-cycle CQF. In this paper, we propose a multi-cycle CQF to address the transmission in multi-link-rate networking, reducing deterministic end-to-end latency and improving link bandwidth utilization. In addition, we formulate the scheduling constraints, being of guiding significance for designing the transmission of multi-link-rate networks, and we design an online scheduling algorithm based on it. We compare the proposed scheme with the single-cycle CQF online scheduling algorithm in hierarchical multi-link-rate networking scenarios, and the evaluation shows that our algorithm achieves better end-to-end ultra-low latency (38.9% reduction) with a smaller schedulability gap compared with single-cycle CQF.

With the recent advances in computer-supported cooperative work systems and increasing popularization of speech-based interfaces, groupware attempting to emulate a knowledgeable participant in a collaborative environment is bound to become a reality in the near future. In this paper, we present IdeaWall, a real-time system that continuously extracts essential information from a verbal discussion and augments that information with web-search materials. IdeaWall provides combinatorial visual stimuli to the participants to facilitate their creative process. We develop three cognitive strategies, from which a prototype application with three display modes was designed, implemented, and evaluated. The results of the user study with twelve groups show that IdeaWall effectively presents visual cues to facilitate verbal creative collaboration for idea generation and sets the stage for future research on intelligent systems that assist collaborative work.