Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods prioritise semantic similarity over task intent, degrading multi-session coherence. We propose MemGuide, a two-stage intent-driven memory selection framework: (1) Intent‑Aligned Retrieval retrieves goal-consistent QA‑formatted memory units; (2) Missing‑Slot Guided Filtering reranks units by slot-completion gain via a chain‑of‑thought reasoner and fine‑tuned LLaMA‑8B filter. We also introduce the MS-TOD, the first multi-session TOD benchmark with 132 diverse personas, 956 task goals, and annotated intent-aligned memory targets. Evaluations on MS-TOD show that MemGuide boosts task success rate by 11% (88%→99%) and reduces dialogue length by 2.84 turns, and matches single‑session performance.

Prompt-based essay writing is an effective and common way to assess students' critical thinking skills. Recent work has evaluated the impressive capabilities of Large Language Models (LLMs) on this task. However, most studies focus primarily on English. Those examining LLMs' performance in Chinese often rely on coarse-grained text quality metrics, overlooking the structural and rhetorical complexities of Chinese essays, particularly across diverse genres. We therefore propose EssayBench, a multi-genre benchmark specifically designed for Chinese essay writing, along with a fine-grained, genre-specific scoring framework that hierarchically aggregates scores to better align with human preferences. The dataset comprises 728 real-world prompts across four major genres (Argumentative, Narrative, Descriptive, and Expository), and includes both Open-Ended and Constrained types. Our evaluation protocol is validated through a comprehensive human agreement study. The results show that our protocol aligns well with human judgments, achieving a highest Spearman's correlation of 0.816 and outperforming coarse-grained evaluation methods by an average of 8.6\%. Finally, we benchmark 15 large LLMs, analyzing their strengths and limitations across genres and instruction types. We believe EssayBench offers a more reliable framework for evaluating Chinese essay generation and provides valuable insights for improving LLMs in this domain.

Zhengyi Zhao, Shubo Zhang, Yiming Du, Bin Liang, Baojun Wang, Zhongyang Li, Binyang Li, Kam-Fai Wong. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Stickers are widely used in online chatting, which can vividly express someone's intention, emotion, or attitude. Existing conversation research typically retrieves stickers based on a single session or the previous textual information, which can not adapt to the multi-modal and multi-session nature of the real-world conversation. To this end, we introduce MultiChat, a new dataset for sticker retrieval facing the multi-modal and multi-session conversation, comprising 1,542 sessions, featuring 50,192 utterances and 2,182 stickers. Based on the created dataset, we propose a novel Intent-Guided Sticker Retrieval (IGSR) framework that retrieves stickers for multi-modal and multi-session conversation history drawing support from intent learning. Specifically, we introduce sticker attributes to better leverage the sticker information in multi-modal conversation, which are incorporated with utterances to construct a memory bank. Further, we extract relevant memories for the current conversation from the memory bank to identify the intent of the current conversation, and then retrieve a sticker to respond guided by the intent. Extensive experiments on our MultiChat dataset reveal the robustness and effectiveness of our IGSR approach in multi-session, multi-modal scenarios.

Erxin Yu, Jing Li, Ming Liao, Qi Zhu, Boyang Xue, Minghui Xu, Baojun Wang, Lanqing Hong, Fei Mi, Lifeng Shang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Cai Ke, Yiming Du, Bin Liang, Yifan Xiang, Lin Gui, Zhongyang Li, Baojun Wang, Yue Yu, Hui Wang, Kam-Fai Wong, Ruifeng Xu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Chinese spelling correction (CSC) is a task that aims to detect and correct the spelling errors that may occur in Chinese texts. However, the Chinese language exhibits a high degree of complexity, characterized by the presence of multiple phonetic representations known as pinyin, which possess distinct tonal variations that can correspond to various characters. Given the complexity inherent in the Chinese language, the CSC task becomes imperative for ensuring the accuracy and clarity of written communication. Recent research has included external knowledge into the model using phonological and visual modalities. However, these methods do not effectively target the utilization of modality information to address the different types of errors. In this paper, we propose a multimodal pretrained language model called DRMSpell for CSC, which takes into consideration the interaction between the modalities. A dynamically reweighting multimodality (DRM) module is introduced to reweight various modalities for obtaining more multimodal information. To fully use the multimodal information obtained and to further strengthen the model, an independent-modality masking strategy (IMS) is proposed to independently mask three modalities of a token in the pretraining stage. Our method achieves state-of-the-art performance on most metrics constituting widely used benchmarks. The findings of the experiments demonstrate that our method is capable of modeling the interactive information between modalities and is also robust to incorrect modal information.

Understanding temporal commonsense concepts, such as times of occurrence and durations is crucial for event-centric language understanding. Reasoning about such temporal concepts in a complex context requires reasoning over both the stated context and the world knowledge that underlines it. A recent study shows massive pre-trained LM still struggle with such temporal reasoning under complex contexts (e.g., dialog) because they only implicitly encode the relevant contexts and fail to explicitly uncover the underlying logical compositions for complex inference, thus may not be robust enough. In this work, we propose to augment LMs with the temporal logic induction ability, which frames the temporal reasoning by defining three modular components: temporal dependency inducer and temporal concept defuzzifier and logic validator. The former two components disentangle the explicit/implicit dependency between temporal concepts across context (before, after, ...) and the specific meaning of fuzzy temporal concepts, respectively, while the validator combines the intermediate reasoning clues for robust contextual reasoning about the temporal concepts. Extensive experimental results on TIMEDIAL, a challenging dataset for temporal reasoning over dialog, show that our method, Logic Induction Enhanced Contextualized TEmporal Reasoning (LECTER), can yield great improvements over the traditional language model for temporal reasoning.

Recently, semantic parsing using hierarchical representations for dialog systems has captured substantial attention. Task-Oriented Parse (TOP), a tree representation with intents and slots as labels of nested tree nodes, has been proposed for parsing user utterances. Previous TOP parsing methods are limited on leveraging lexicon resources, which are often used to guide the real dialog system. To mitigate this issue, we first propose a novel span-splitting representation for span-based parser that outperforms existing methods. Then we present a novel lexicon-injected semantic parser, which collects slot labels of tree representation as a lexicon, and injects lexical features to the span representation of parser. An additional slot disambiguation technique is involved to remove inappropriate span match occurrences from the lexicon. Experiments show that our best parser produces a new state-of-the-art result (87.62%) on the TOP dataset, and also confirm the effectiveness of our proposed lexicon-injected parser and slot disambiguation model.

Previous audio-text retrieval (ATR) methods primarily concentrate on constructing contrastive pairs between entire audio clips and full caption sentences, while neglecting fine-grained cross-modal relationships. In this letter, we first introduce a weighted token-level alignment (WTA) module for ATR to learn fine-grained semantic interactions. Besides, due to the unavailability of manually labeling the fine-grained sequential correspondence between audio-text pairs, we attempt to model ATR as a cooperative game process to flexibly handle the uncertainty during audio-text semantic interactions. Specifically, we treat audio frames and text words as players and present a game theoretic interaction (GTI) method to assess potential correspondence between audio frames and text words, which can also be seen as an additional learning signal to improve the pure audio-text contrastive learning. Furthermore, to implement multi-level WTA and GTI, we develop a token cluster module to cluster the frames/words and calculate the interaction scores between the clustered tokens. Experiments show that our WTA significantly improves the ATR performance on multiple datasets. By combining our GTI, the retrieval performance is further boosted by a large margin.

Baojun Wang, Zhao Zhang, Kun Xu, Guang-Yuan Hao, Yuyang Zhang, Lifeng Shang, Linlin Li, Xiao Chen, Xin Jiang, Qun Liu. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.

We describe the design and implementation of DetTrace, a reproducible container abstraction for Linux implemented in user space. All computation that occurs inside a DetTrace container is a pure function of the initial filesystem state of the container. Reproducible containers can be used for a variety of purposes, including replication for fault-tolerance, reproducible software builds and reproducible data analytics. We use DetTrace to achieve, in an automatic fashion, reproducibility for 12,130 Debian package builds, containing over 800 million lines of code, as well as bioinformatics and machine learning workflows. We show that, while software in each of these domains is initially irreproducible, DetTrace brings reproducibility without requiring any hardware, OS or application changes. DetTrace's performance is dictated by the frequency of system calls: IO-intensive software builds have an average overhead of 3.49x, while a compute-bound bioinformatics workflow is under 2%.

Synthetic biology aims to engineer and redesign biological systems for useful real-world applications in biomanufacturing, biosensing and biotherapy following a typical design-build-test cycle. Inspired from computer science and electronics, synthetic gene circuits have been designed to exhibit control over the flow of information in biological systems. Two types are Boolean logic inspired TRUE or FALSE digital logic and graded analog computation. Key principles for gene circuit engineering include modularity, orthogonality, predictability and reliability. Initial circuits in the field were small and hampered by a lack of modular and orthogonal components, however in recent years the library of available parts has increased vastly. New tools for high throughput DNA assembly and characterization have been developed enabling rapid prototyping, systematic in situ characterization, as well as automated design and assembly of circuits. Recently implemented computing paradigms in circuit memory and distributed computing using cell consortia will also be discussed. Finally, we will examine existing challenges in building predictable large-scale circuits including modularity, context dependency and metabolic burden as well as tools and methods used to resolve them. These new trends and techniques have the potential to accelerate design of larger gene circuits and result in an increase in our basic understanding of circuit and host behaviour.