Related papers: LoSemB: Logic-Guided Semantic Bridging for Inducti…

Solving constraints involving inductive (aka recursive) definitions is challenging. State-of-the-art SMT/CHC solvers and first-order logic provers provide only limited support for solving such constraints, especially when they involve,…

The trade-off between expressiveness and interpretability remains a core challenge when building human-centric predictive models for classification and decision-making. While symbolic rules offer interpretability, they often lack…

In the competitive landscape of sponsored search, balancing retrieval quality with production latency is a critical challenge. While large retrieval models based on Small Language Models (SLMs) such as Qwen3-Embedding-4B/8B set strong upper…

Prevalent retrieval-based tool-use pipelines struggle with a dual semantic challenge: their retrievers often employ encoders that fail to capture complex semantics, while the Large Language Model (LLM) itself lacks intrinsic tool knowledge…

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…

Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significant burden on token representations to encode all…

Existing sequential recommendation models, even advanced diffusion-based approaches, often struggle to capture the rich semantic intent underlying user behavior, especially for new users or long-tail items. This limitation stems from their…

Agents utilizing tools powered by large language models (LLMs) or vision-language models (VLMs) have demonstrated remarkable progress in diverse tasks across text and visual modalities. Unlike traditional tools such as calculators, which…

Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training practices largely rely on supervised fine-tuning (SFT) over…

Large Language Models (LLMs) are prone to critical failure modes, including \textit{intrinsic faithfulness hallucinations} (also known as confabulations), where a response deviates semantically from the provided context. Frameworks designed…

[Context] Large Language Models (LLMs) are increasingly used to assist qualitative research in Software Engineering (SE), yet the methodological implications of this usage remain underexplored. Their integration into interpretive processes…

Recent advancements in large language models (LLMs) have catalyzed the rise of reasoning-intensive inference paradigms, where models perform explicit step-by-step reasoning before generating final answers. While such approaches improve…

Large language models have demonstrated exceptional performance, yet struggle with complex tasks such as numerical reasoning, plan generation. Integrating external tools, such as calculators and databases, into large language models (LLMs)…

Reading comprehension, a fundamental cognitive ability essential for knowledge acquisition, is a complex skill, with a notable number of learners lacking proficiency in this domain. This study introduces innovative tasks for Brain-Computer…

Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent studies show that Multimodal Large Language Models (MLLMs)…

Recent advanced methods in Natural Language Understanding for Task-oriented Dialogue (TOD) Systems (e.g., intent detection and slot filling) require a large amount of annotated data to achieve competitive performance. In reality,…

Large language models (LLMs) that are tuned with instructions have demonstrated remarkable capabilities in various tasks and languages. However, their ability to generalize to underrepresented languages is limited due to the scarcity of…

Despite the advancements of open-source large language models (LLMs), e.g., LLaMA, they remain significantly limited in tool-use capabilities, i.e., using external tools (APIs) to fulfill human instructions. The reason is that current…

The tool-using capability of large language models (LLMs) enables them to access up-to-date external information and handle complex tasks. Current approaches to enhancing this capability primarily rely on distilling advanced models by data…

Equipping Large Language Models (LLMs) with external tools enables them to solve complex real-world problems. However, the robustness of existing methods remains a critical challenge when confronting novel or evolving tools. Existing…