Unsupervised multimodal semantic discovery aims to learn discriminative representations from multimodal data. However, existing methods suffer from two key limitations. First, they only align instances across modalities without modeling semantic-level consistency, which fails to mitigate semantic bias caused by the gaps among feature distributions of multiple modalities. Second, they inevitably generate incorrect negative pairs during contrastive learning, pushing semantically similar samples apart. To address these challenges, we propose GLAD (Global and Local semantic Alignment for unsupervised multimodal semantic Discovery), which aligns multimodal data at both global and local semantic levels. At the global level, GSA integrates multi-modal features into a shared space and employs joint clustering via optimal transport to capture common semantic patterns while mitigating cross-modality semantic bias. At the local level, LSA adaptively weights samples within each cluster based on their semantic importance, alleviating the effect of incorrect negative pairs. Through the joint optimization of GSA and LSA, GLAD effectively captures both the global semantic structure and the local semantic nuances of multimodal data. Extensive experiments on three benchmark datasets demonstrate GLAD significantly outperforms state-of-the-art methods, with an average improvement of 3.22%.

Automated schedule generation for multitask from natural language descriptions has huge potential in modern industry.While classic methods bypass language complexities by using preformatted matrices, and recent LLM+solver approaches introduce new fragilities by relying on solver-specific code generation.This raises critical questions: Can large language models (LLMs) solve this NL ⇒ Schedule task end-to-end well (RQ1)?If the answer is "no", where do they fall short (RQ2)?And how can their capabilities be enhanced (RQ3)?To answer these questions, we introduce NL ⇒ Schedule, the first benchmark for this task, equipped with a dataset of 240 descriptionschedule pairs constructed from real-world materials and a rigorous evaluation suite.Our evaluation of nine state-of-the-art LLMs reveals the limitations of different LLMs in procedure grounding and the strengths of advanced LLMs in global planning via local analysis.To address these shortcomings, we propose MANS, a novel multi-agent framework.Extensive experiments show that MANS achieves more robust performance comparable to six state-ofthe-art LLM+solver methods.We hope NL ⇒ Schedule and MANS will serve as a solid foundation for automatic scheduling.The code and dataset are available in https://github.com/ SCUNLP/NL2Schedule

Automatic extraction of procedural graphs from documents creates a low-cost way for users to easily understand a complex procedure by skimming visual graphs.Despite the progress in recent studies, it remains unanswered: whether the existing studies have well solved this task (Q1) and whether the emerging large language models (LLMs) can bring new opportunities to this task (Q2).To this end, we propose a new benchmark PAGED, equipped with a large high-quality dataset and standard evaluations.It investigates five state-of-the-art baselines, revealing that they fail to extract optimal procedural graphs well because of their heavy reliance on hand-written rules and limited available data.We further involve three advanced LLMs in PAGED and enhance them with a novel self-refine strategy.The results point out the advantages of LLMs in identifying textual elements and their gaps in building logical structures.We hope PAGED can serve as a major landmark for automatic procedural graph extraction and the investigations in PAGED can provide valuable insights into the research on logical reasoning among non-sequential elements.The code and dataset are available in https://github.com/SCUNLP/PAGED.

It is time-saving to build a reading assistant for customer service representations (CSRs) when reading user manuals, especially informationrich ones.Current solutions don't fit the online custom service scenarios well due to the lack of attention to user questions and possible responses.Hence, we propose to develop a timesaving and careful reading assistant for CSRs, named CARE.It can help the CSRs quickly find proper responses from the user manuals via explicit clue chains.Specifically, each of the clue chains is formed by inferring over the user manuals, starting from the question clue aligned with the user question and ending at a possible response.To overcome the shortage of supervised data, we adopt the self-supervised strategy for model learning.The offline experiment shows that CARE is efficient in automatically inferring accurate responses from the user manual.The online experiment further demonstrates the superiority of CARE to reduce CSRs' reading burden and keep high service quality, in particular with > 35% decrease in time spent and keeping a > 0.75 ICC score.