Hongru (Merlin) Wang

Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. However, their parametric knowledge may conflict with the information provided in the context—this phenomenon, known as \textitcontext-memory knowledge conflicts, can lead to undesirable model behaviour, such as reliance on outdated or incorrect information. Analysing the internal activations of LLMs, we find that they can internally register the signals of knowledge conflict at mid-layers. Such signals allow us to detect whether a knowledge conflict occurs and use \textitinference-time intervention strategies to resolve it. In this work, we propose SpARE, a \textittraining-free representation engineering method that uses pre-trained sparse auto-encoders (SAEs) to control the knowledge selection behaviour of LLMs. SpARE identifies the functional features that control the knowledge selection behaviours and applies them to edit the internal activations of LLMs at inference time. Our experimental results show that SpARE can effectively control the usage of either knowledge source to resolve knowledge conflict in open-domain question-answering tasks, surpassing existing representation engineering methods (+10%) as well as contrastive decoding methods (+15%).

Since the advent of large language models (LLMs), the field of tool learning has remained very active in solving various tasks in practice, including but not limited to information retrieval. This half-day tutorial provides basic concepts of this field and an overview of recent advancements with several applications. In specific, we start with some foundational components and architecture of tool learning (i.e., cognitive tool and physical tool), and then we categorize existing studies in this field into tool-augmented learning and tool-oriented learning, and introduce various learning methods to empower LLMs this kind of capability. Furthermore, we provide several cases about when, what, and how to use tools in different applications. We end with some open challenges and several potential research directions for future studies. We believe this tutorial is suited for both researchers at different stages (introductory, intermediate, and advanced) and industry practitioners who are interested in LLMs and tool learning.

This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and parametric knowledge. Our focus is on three categories of knowledge conflicts: context-memory, inter-context, and intra-memory conflict. These conflicts can significantly impact the trustworthiness and performance of LLMs, especially in real-world applications where noise and misinformation are common. By categorizing these conflicts, exploring the causes, examining the behaviors of LLMs under such conflicts, and reviewing available solutions, this survey aims to shed light on strategies for improving the robustness of LLMs, thereby serving as a valuable resource for advancing research in this evolving area.

Large Language Models (LLMs) can interact with the real world by connecting with versatile external APIs, resulting in better problem-solving and task automation capabilities. Previous research primarily either focuses on APIs with limited arguments from a single source or overlooks the complex dependency relationship between different APIs. However, it is essential to utilize multiple APIs collaboratively from various sources, especially for complex user instructions. In this paper, we introduce MetaBench, the first benchmark to evaluate LLMs’ ability to plan and execute multiple APIs from various sources in order to complete the user’s task. Specifically, we consider two significant challenges in multiple APIs: 1) graph structures: some APIs can be executed independently while others need to be executed one by one, resulting in graph-like execution order; and 2) permission constraints: which source is authorized to execute the API call. We have experimental results on 9 distinct LLMs; e.g., GPT-4o achieves only a 2.0% success rate at the most complex instruction, revealing that the existing state-of-the-art LLMs still cannot perform well in this situation even with the help of in-context learning and finetuning. Our code and data are publicly available at \urlhttps://github.com/ruleGreen/AppBench.