Automatic movie narration targets at creating video-aligned plot descriptions to assist visually impaired audiences. It differs from standard video captioning in that it requires not only describing key visual details but also inferring the plots developed across multiple movie shots, thus posing unique and ongoing challenges. To advance the development of automatic movie narrating systems, we first revisit the limitations of existing datasets and develop a large-scale, bilingual movie narration dataset, Movie101v2. Second, taking into account the essential difficulties in achieving applicable movie narration, we break the long-term goal into three progressive stages and tentatively focus on the initial stages featuring understanding within individual clips. We also introduce a new narration assessment to align with our staged task goals. Third, using our new dataset, we baseline several leading large vision-language models, including GPT-4V, and conduct in-depth investigations into the challenges current models face for movie narration generation. Our findings reveal that achieving applicable movie narration generation is a fascinating goal that requires thorough research.

Machine learning models have made incredible progress, but they still struggle when applied to examples from unseen domains. This study focuses on a specific problem of domain generalization, where a model is trained on one source domain and tested on multiple target domains that are unseen during training. We propose IMO: Invariant features Masks for Out-of-Distribution text classification, to achieve OOD generalization by learning invariant features. During training, IMO would learn sparse mask layers to remove irrelevant features for prediction, where the remaining features keep invariant. Additionally, IMO has an attention module at the token level to focus on tokens that are useful for prediction. Our comprehensive experiments show that IMO substantially outperforms strong baselines in terms of various evaluation metrics and settings.

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and effective strategy for preventing unauthorized model distribution. However, this paper identifies an inherent flaw in the current paradigm of trigger set watermarking: evasion adversaries can readily exploit the shortcuts created by models memorizing watermark samples that deviate from the main task distribution, significantly impairing their generalization in adversarial settings. To counteract this, we leverage diffusion models to synthesize unrestricted adversarial examples as trigger sets. By learning the model to accurately recognize them, unique watermark behaviors are promoted through knowledge injection rather than error memorization, thus avoiding exploitable shortcuts. Furthermore, we uncover that the resistance of current trigger set watermarking against removal attacks primarily relies on significantly damaging the decision boundaries during embedding, intertwining unremovability with adverse impacts. By optimizing the knowledge transfer properties of protected models, our approach conveys watermark behaviors to extraction surrogates without aggressively decision boundary perturbation. Experimental results on CIFAR-10/100 and Imagenette datasets demonstrate the effectiveness of our method, showing not only improved robustness against evasion adversaries but also superior resistance to watermark removal attacks compared to state-of-the-art solutions.

GPT-4 demonstrates high accuracy in medical QA tasks, leading with an accuracy of 86.70%, followed by Med-PaLM 2 at 86.50%. However, around 14% of errors remain. Additionally, current works use GPT-4 to only predict the correct option without providing any explanation and thus do not provide any insight into the thinking process and reasoning used by GPT-4 or other LLMs. Therefore, we introduce a new domain-specific error taxonomy derived from collaboration with medical students. Our GPT-4 USMLE Error (G4UE) dataset comprises 4153 GPT-4 correct responses and 919 incorrect responses to the United States Medical Licensing Examination (USMLE) respectively. These responses are quite long (258 words on average), containing detailed explanations from GPT-4 justifying the selected option. We then launch a large-scale annotation study using the Potato annotation platform and recruit 44 medical experts through Prolific, a well-known crowdsourcing platform. We annotated 300 out of these 919 incorrect data points at a granular level for different classes and created a multi-label span to identify the reasons behind the error. In our annotated dataset, a substantial portion of GPT-4's incorrect responses is categorized as a "Reasonable response by GPT-4," by annotators. This sheds light on the challenge of discerning explanations that may lead to incorrect options, even among trained medical professionals. We also provide medical concepts and medical semantic predications extracted using the SemRep tool for every data point. We believe that it will aid in evaluating the ability of LLMs to answer complex medical questions. We make the resources available at https://github.com/roysoumya/usmle-gpt4-error-taxonomy .

Vision-Language Models (VLMs) are a significant technique for Artificial General Intelligence (AGI). With the fast growth of AGI, the security problem become one of the most important challenges for VLMs. In this paper, through extensive experiments, we demonstrate the vulnerability of the conventional adaptation methods for VLMs, which may bring significant security risks. In addition, as the size of the VLMs increases, performing conventional adversarial adaptation techniques on VLMs results in high computational costs. To solve these problems, we propose a parameter-efficient \underline{Adv}ersarial adaptation method named \underline{AdvLoRA} by \underline{Lo}w-\underline{R}ank \underline{A}daptation. At first, we investigate and reveal the intrinsic low-rank property during the adversarial adaptation for VLMs. Different from LoRA, we improve the efficiency and robustness of adversarial adaptation by designing a novel reparameterizing method based on parameter clustering and parameter alignment. In addition, an adaptive parameter update strategy is proposed to further improve the robustness. By these settings, our proposed AdvLoRA alleviates the model security and high resource waste problems. Extensive experiments demonstrate the effectiveness and efficiency of the AdvLoRA.

Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. Compared with original LLMs, LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems that need long-term and complex agent-environment interactions. The key component to support agent-environment interactions is the memory of the agents. While previous studies have proposed many promising memory mechanisms, they are scattered in different papers, and there lacks a systematical review to summarize and compare these works from a holistic perspective, failing to abstract common and effective designing patterns for inspiring future studies. To bridge this gap, in this paper, we propose a comprehensive survey on the memory mechanism of LLM-based agents. In specific, we first discuss ''what is'' and ''why do we need'' the memory in LLM-based agents. Then, we systematically review previous studies on how to design and evaluate the memory module. In addition, we also present many agent applications, where the memory module plays an important role. At last, we analyze the limitations of existing work and show important future directions. To keep up with the latest advances in this field, we create a repository at \url{https://github.com/nuster1128/LLM_Agent_Memory_Survey}.

Information Extraction (IE) is a transformative process that converts unstructured text data into a structured format by employing entity and relation extraction (RE) methodologies. The identification of the relation between a pair of entities plays a crucial role within this framework. Despite the existence of various techniques for relation extraction, their efficacy heavily relies on access to labeled data and substantial computational resources. In addressing these challenges, Large Language Models (LLMs) emerge as promising solutions; however, they might return hallucinating responses due to their own training data. To overcome these limitations, Retrieved-Augmented Generation-based Relation Extraction (RAG4RE) in this work is proposed, offering a pathway to enhance the performance of relation extraction tasks. This work evaluated the effectiveness of our RAG4RE approach utilizing different LLMs. Through the utilization of established benchmarks, such as TACRED, TACREV, Re-TACRED, and SemEval RE datasets, our aim is to comprehensively evaluate the efficacy of our RAG4RE approach. In particularly, we leverage prominent LLMs including Flan T5, Llama2, and Mistral in our investigation. The results of our study demonstrate that our RAG4RE approach surpasses performance of traditional RE approaches based solely on LLMs, particularly evident in the TACRED dataset and its variations. Furthermore, our approach exhibits remarkable performance compared to previous RE methodologies across both TACRED and TACREV datasets, underscoring its efficacy and potential for advancing RE tasks in natural language processing.

Code generation with Large Language Models (LLMs) has been extensively studied and achieved remarkable progress. As a complementary aspect to code generation, test case generation is of crucial importance in ensuring the quality and reliability of code. However, using LLMs as test case generators has been much less explored. Current research along this line primarily focuses on enhancing code generation with assistance from test cases generated by LLMs, while the performance of LLMs in test case generation alone has not been comprehensively examined. To bridge this gap, we conduct extensive experiments to study how well LLMs can generate high-quality test cases. We find that as the problem difficulty increases, state-of-the-art LLMs struggle to generate correct test cases, largely due to their inherent limitations in computation and reasoning. To mitigate this issue, we further propose a multi-agent framework called \emph{TestChain} that decouples the generation of test inputs and test outputs. Notably, TestChain uses a ReAct format conversation chain for LLMs to interact with a Python interpreter in order to provide more accurate test outputs. Our results indicate that TestChain outperforms the baseline by a large margin. Particularly, in terms of the accuracy of test cases, TestChain using GPT-4 as the backbone achieves a 13.84\% improvement over the baseline on the LeetCode-hard dataset.

The dynamic nature of knowledge in an ever-changing world presents challenges for language models trained on static data; the model in the real world often requires not only acquiring new knowledge but also overwriting outdated information into updated ones. To study the ability of language models for these time-dependent dynamics in human language, we introduce a novel task, EvolvingQA, a temporally evolving question-answering benchmark designed for training and evaluating LMs on an evolving Wikipedia database. The construction of EvolvingQA is automated with our pipeline using large language models. We uncover that existing continual learning baselines suffer from updating and removing outdated knowledge. Our analysis suggests that models fail to rectify knowledge due to small weight gradients. In addition, we elucidate that language models particularly struggle to reflect the change of numerical or temporal information. Our work aims to model the dynamic nature of real-world information, suggesting faithful evaluations of the evolution-adaptability of language models.

Efficient knowledge management plays a pivotal role in augmenting both the operational efficiency and the innovative capacity of businesses and organizations. By indexing knowledge through vectorization, a variety of knowledge retrieval methods have emerged, significantly enhancing the efficacy of knowledge management systems. Recently, the rapid advancements in generative natural language processing technologies paved the way for generating precise and coherent answers after retrieving relevant documents tailored to user queries. However, for enterprise knowledge bases, assembling extensive training data from scratch for knowledge retrieval and generation is a formidable challenge due to the privacy and security policies of private data, frequently entailing substantial costs. To address the challenge above, in this paper, we propose EKRG, a novel Retrieval-Generation framework based on large language models (LLMs), expertly designed to enable question-answering for Enterprise Knowledge bases with limited annotation costs. Specifically, for the retrieval process, we first introduce an instruction-tuning method using an LLM to generate sufficient document-question pairs for training a knowledge retriever. This method, through carefully designed instructions, efficiently generates diverse questions for enterprise knowledge bases, encompassing both fact-oriented and solution-oriented knowledge. Additionally, we develop a relevance-aware teacher-student learning strategy to further enhance the efficiency of the training process. For the generation process, we propose a novel chain of thought (CoT) based fine-tuning method to empower the LLM-based generator to adeptly respond to user questions using retrieved documents. Finally, extensive experiments on real-world datasets have demonstrated the effectiveness of our proposed framework.