With the rapid advancement of large language models (LLMs), recent researchers have increasingly focused on the superior capabilities of LLMs in text/code understanding and generation to tackle text-to-SQL tasks. Traditional approaches adopt schema linking to first eliminate redundant tables and columns and prompt LLMs for SQL generation. However, they often struggle with accurately identifying corresponding tables and columns, due to discrepancies in naming conventions between natural language questions (NL) and database schemas. Besides, existing methods overlook the challenge of effectively transforming structure information from NL into SQL. To address these limitations, we introduce UCS-SQL, a novel text-to-SQL framework, uniting both content and structure pipes to bridge the gap between NL and SQL. Specifically, the content pipe focuses on identifying key content within the original content, while the structure pipe is dedicated to transforming the linguistic structure from NL to SQL. Additionally, we strategically selects few-shot examples by considering both the SQL Skeleton and Question Expression (SS-QE selection method), thus providing targeted examples for SQL generation. Experimental results on BIRD and Spider demonstrate the effectiveness of our UCS-SQL framework.

Multilingual spoken language understanding (SLU) involves intent detection (ID) and slot filling (SF) across multiple languages. The inherent linguistic diversity presents significant challenges in achieving performance comparable to traditional SLU. Recent studies have attempted to improve multilingual SLU performance by sharing multilingual encoders. However, these approaches have not directly established information flow between languages. To address this, we first demonstrate the feasibility of such information transfer and pinpoint the key challenges: prediction error mitigation and multilingual slot alignment. We then propose the INformation Transfer network (INT) to tackle these challenges. The gate unit in INT controls the information flow between languages, reducing the adverse impact of prediction errors on both ID and SF. Additionally, we reformulate SF as a span prediction problem and introduce a slot-matching attention mechanism to achieve slot alignment across languages. Experimental results on the MASSIVE and MASSIVE-UG datasets show that our model outperforms all baselines in overall accuracy across all languages, and demonstrates robust performance when different languages are used as the source.

This paper presents the approach we employed in SemEval-2025 Task 11: “Bridging the Gap in Text-Based Emotion Detection.” The core objective of this shared task is emotion perception, focusing on determining the emotion the speaker is likely expressing when uttering a sentence or short text fragment, as perceived by the majority. In this task, we applied a prompt optimization strategy based on in-context learning, combined with data augmentation and ensemble voting techniques, to significantly enhance the model’s performance. Through these optimizations, the model demonstrated improved accuracy and stability in emotion detection. Ultimately, in both Track A (Multi-label Emotion Detection) and Track B (Emotion Intensity Prediction), our approach achieved top-3 rankings across multiple languages, showcasing the effectiveness and cross-lingual adaptability of our method.

The paper presents our system developed for SemEval-2025 Task 8, which focuses on table question answering (TQA). The TQA tasks face challenges due to the characteristics of real-world tabular data, such as large size, incomplete column semantics, and entity ambiguity. To address these issues, we propose a large language model (LLM)-powered and programming-based framework, named Flow-of-Table-Reasoning. We introduce the table schema integrating verbalized structure and semantics for query decomposition and programming, enabling a holistic understanding of tables and the ability to process large-size tables. We design a multi-step schema linking plan to derive a focused table schema that retains only information relevant to the query, aiming to eliminate ambiguity and reduce hallucinations. Furthermore, we incorporate reasoning workflow into an iterative thinking architecture, allowing incremental cycles of thinking, reasoning and reflection. Our system achieves first place on both TQA and Lite TQA subtasks.

In this paper, we present a novel pipeline for the XLLM Shared Task-III: Large Language Model for Structural Reasoning (LLM-SR). Our pipeline addresses key challenges in automatic process-reward training data construction, such as high manual annotation costs, limited accuracy of large models in structured data processing, and dependency on auxiliary information for validation. To overcome these limitations, we first decompose the construction process into extraction and validation phases. Leveraging model-generated annotations, we produce pseudo-labeled data and iteratively refine model performance. Second, by analyzing structured data patterns, we encode structural constraints into a rule-based module and fine-tune the model with Gradient Reward Policy Optimization (GRPO), significantly improving structured data extraction success rates. Finally, we train the model to generate critical responses that assess evidence-conclusion relationships, thus enhancing validation reliability. Experimental results demonstrate that our pipeline outperforms models with an order of magnitude more parameters and achieves the first position on the task.

“本技术报告详细介绍了我们团队参加第四届中文空间语义理解评测(SpaCE2024)的方法和成果。SpaCE2024旨在全面测试机器对中文空间语义的理解能力,包括空间信息实体识别、空间信息实体识别、空间信息异常识别、空间方位信息推理和空间异形同义识别五个不同的任务。我们团队采用精心设计的prompt并结合微调的方式激发大语言模型的空间语义理解能力,构建了一个高效的空间语义理解系统。在最终的评估中,我们在空间信息实体识别题目中准确率为0.8947,在空间信息实体识别题目中准确率为0.9364,在空间信息异常识别题目中准确率为0.8480,在空间方位信息推理题目中准确率为0.3471,在空间异形同义识别题目中准确率为0.5631,测试集综合准确率为0.6024,排名第一。”

“本文描述了队伍“TeleAI”在CCL2024古文历史事件类型抽取评测任务(CHED2024)中提交的参赛系统。该任务旨在自动识别出古代文本中的事件触发词与事件类型,其中事件类型判别被分为粗粒度和细粒度的事件类型判别两部分。为了提高古文历史事件类型抽取的性能,我们结合了大模型和小模型,并采用了半监督自训练的方法。在最终的评估中,我们在触发词识别任务得分0.763,粗粒度事件类型判别任务得分0.842,细粒度事件类型判别任务得分0.779,综合得分0.791,在所有单项任务和综合评分上均排名第一。”

Hierarchical text classification aims at categorizing texts into a multi-tiered tree-structured hierarchy of labels. Existing methods pay more attention to capture hierarchy-aware text feature by exploiting explicit parent-child relationships, while interactions between peer labels are rarely taken into account, resulting in severe label confusion within each layer. In this work, we propose a novel Dual Prompt Tuning (DPT) method, which emphasizes identifying discrimination among peer labels by performing contrastive learning on each hierarchical layer. We design an innovative hand-crafted prompt containing slots for both positive and negative label predictions to cooperate with contrastive learning. In addition, we introduce a label hierarchy self-sensing auxiliary task to ensure cross-layer label consistency. Extensive experiments demonstrate that DPT achieves significant improvements and outperforms the current state-of-the-art methods on BGC and RCV1-V2 benchmark datasets.

This paper describes the participation of team “TeleAI” in the third International Chinese Ancient Chinese Language Information Processing Evaluation (EvalHan24). The competition comprises a joint task of sentence segmentation and punctuation, categorized into open and closed tracks based on the models and data used. In the final evaluation, our system achieved significantly better results than the baseline. Specifically, in the closed-track sentence segmentation task, we obtained an F1 score of 0.8885, while in the sentence punctuation task, we achieved an F1 score of 0.7129.

In this paper, we present TeleChat, a collection of large language models (LLMs) with parameters of 7 billion and 12 billion. TeleChat is initially pretrained on an extensive corpus containing a diverse collection of texts from both English and Chinese languages, encompassing trillions of tokens. Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe. We evaluate the performance of TeleChat on various tasks, including general dialogue generation, language understanding, mathematics, reasoning, code generation, and knowledge-based question answering. Our findings indicate that TeleChat achieves state-of-the-art performance to other open-source models of similar size across a wide range of public benchmarks. To support future research and applications utilizing LLMs, we release the fine-tuned model checkpoints of TeleChat-7B and TeleChat-12B, along with code and a portion of our filtered high-quality pretraining data, to the public community.