Related papers: Self-Guided Function Calling in Large Language Mod…

In speech emotion recognition (SER), using predefined features without considering their practical importance may lead to high dimensional datasets, including redundant and irrelevant information. Consequently, high-dimensional learning…

Code generation, the task of creating executable programs from natural language requirements, has recently seen tremendous advances through Chain-of-Thought (CoT) reasoning, which enables Large Language Models (LLMs) to develop high-level…

Tool learning aims to augment large language models (LLMs) with diverse tools, enabling them to act as agents for solving practical tasks. Due to the limited context length of tool-using LLMs, adopting information retrieval (IR) models to…

Tool-augmented large language models (LLMs) are attracting widespread attention when accessing up-to-date knowledge and alleviating hallucination issues. Nowadays, advanced closed-source LLMs (e.g., ChatGPT) have demonstrated surprising…

Large language models (LLMs) have shown superior performance without task-specific fine-tuning. Despite the success, the knowledge stored in the parameters of LLMs could still be incomplete and difficult to update due to the computational…

Large language models excel as conversational agents, but their capabilities can be further extended through tool usage, i.e.: executable code, to enhance response accuracy or address specialized domains. Current approaches to enable tool…

Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored. Existing attacks on LLM reasoning are constrained by specific settings or…

As large language models (LLMs) advance, their inability to autonomously execute tasks by directly interacting with external tools remains a critical limitation. Traditional methods rely on inputting tool descriptions as context, which is…

Large language models (LLMs) have significantly advanced autonomous agents, particularly in zero-shot tool usage, also known as function calling. This research delves into enhancing the function-calling capabilities of LLMs by exploring…

Large Language Models (LLMs) have emerged as powerful tools for generating coherent text, understanding context, and performing reasoning tasks. However, they struggle with temporal reasoning, which requires processing time-related…

Sequential Recommender Systems (SRS) have become a cornerstone of online platforms, leveraging users' historical interaction data to forecast their next potential engagement. Despite their widespread adoption, SRS often grapple with the…

Large language models (LLMs) have enabled a wide variety of real-world applications in various domains. However, creating a high-performing application with high accuracy remains challenging, particularly for subjective tasks like emotion…

Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Traditional inference time scaling methods utilize scalar reward…

Modern Language Models (LMs) are capable of following long and complex instructions that enable a large and diverse set of user requests. While Information Retrieval (IR) models use these LMs as the backbone of their architectures,…

Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set…

Tool learning, which allows Large Language Models (LLMs) to leverage external tools for solving complex user tasks, has emerged as a promising avenue for extending model capabilities. However, existing approaches primarily focus on data…

Due to the dynamically evolving nature of real-world query streams, relevance models struggle to generalize to practical search scenarios. A sophisticated solution is self-evolution techniques. However, in large-scale industrial settings…

Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal…

Tool invocation significantly enhances the capabilities of Large Language Models (LLMs), yet challenges persist, particularly in complex task scenarios. Current methods, such as instruction-enhanced reasoning and supervised fine-tuning,…

Large Language Models (LLMs) have recently emerged as promising tools for recommendation thanks to their advanced textual understanding ability and context-awareness. Despite the current practice of training and evaluating LLM-based…