We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at //github.com/opendatalab/CHARM .
相關內容
Generative AI (GAI) offers unprecedented opportunities for research and innovation, but its commercialization has raised concerns about transparency, reproducibility, and safety. Many open GAI models lack the necessary components for full understanding and reproducibility, and some use restrictive licenses whilst claiming to be ``open-source''. To address these concerns, we propose the Model Openness Framework (MOF), a ranked classification system that rates machine learning models based on their completeness and openness, following principles of open science, open source, open data, and open access. The MOF requires specific components of the model development lifecycle to be included and released under appropriate open licenses. This framework aims to prevent misrepresentation of models claiming to be open, guide researchers and developers in providing all model components under permissive licenses, and help individuals and organizations identify models that can be safely adopted without restrictions. By promoting transparency and reproducibility, the MOF combats ``openwashing'' practices and establishes completeness and openness as primary criteria alongside the core tenets of responsible AI. Wide adoption of the MOF will foster a more open AI ecosystem, benefiting research, innovation, and adoption of state-of-the-art models.
Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs' training data, it could explicitly or implicitly include test data, leading to LLMs being more susceptible to data contamination. However, due to the opacity of training data, the black-box access of models, and the rapid growth of synthetic training data, detecting and mitigating data contamination for LLMs faces significant challenges. In this paper, we propose CDD, which stands for Contamination Detection via output Distribution for LLMs. CDD necessitates only the sampled texts to detect data contamination, by identifying the peakedness of LLM's output distribution. To mitigate the impact of data contamination in evaluation, we also present TED: Trustworthy Evaluation via output Distribution, based on the correction of LLM's output distribution. To facilitate this study, we introduce two benchmarks, i.e., DetCon and ComiEval, for data contamination detection and contamination mitigation evaluation tasks. Extensive experimental results show that CDD achieves the average relative improvements of 21.8\%-30.2\% over other contamination detection approaches in terms of Accuracy, F1 Score, and AUC metrics, and can effectively detect implicit contamination. TED substantially mitigates performance improvements up to 66.9\% attributed to data contamination across various contamination setups. In real-world applications, we reveal that ChatGPT exhibits a high potential to suffer from data contamination on HumanEval benchmark.
Expressive speech-to-speech translation (S2ST) is a key research topic in seamless communication, which focuses on the preservation of semantics and speaker vocal style in translated speech. Early works synthesized speaker style aligned speech in order to directly learn the mapping from speech to target speech spectrogram. Without reliance on style aligned data, recent studies leverage the advances of language modeling (LM) and build cascaded LMs on semantic and acoustic tokens. This work proposes SeamlessExpressiveLM, a single speech language model for expressive S2ST. We decompose the complex source-to-target speech mapping into intermediate generation steps with chain-of-thought prompting. The model is first guided to translate target semantic content and then transfer the speaker style to multi-stream acoustic units. Evaluated on Spanish-to-English and Hungarian-to-English translations, SeamlessExpressiveLM outperforms cascaded LMs in both semantic quality and style transfer, meanwhile achieving better parameter efficiency.
Exchangeability concerning a continuous exposure, X, implies no confounding bias when identifying average exposure effects of X, AEE(X). When X is measured with error (Xep), two challenges arise in identifying AEE(X). Firstly, exchangeability regarding Xep does not equal exchangeability regarding X. Secondly, the non-differential error assumption (NDEA) could be overly stringent in practice. To address them, this article proposes unifying exchangeability and exposure and confounder measurement errors with three novel concepts. The first, Probabilistic Exchangeability (PE), states that the outcomes of those with Xep=e are probabilistically exchangeable with the outcomes of those truly exposed to X=eT. The relationship between AEE(Xep) and AEE(X) in risk difference and ratio scales is mathematically expressed as a probabilistic certainty, termed exchangeability probability (Pe). Squared Pe (Pe2) quantifies the extent to which AEE(Xep) differs from AEE(X) due to exposure measurement error through mechanisms not akin to confounding mechanisms. The coefficient of determination (R2) in the regression of Xep against X may sometimes be sufficient to measure Pe2. The second concept, Emergent Pseudo Confounding (EPC), describes the bias introduced by exposure measurement error through mechanisms akin to confounding mechanisms. PE requires controlling for EPC, which is weaker than NDEA. The third, Emergent Confounding, describes when bias due to confounder measurement error arises. Adjustment for E(P)C can be performed like confounding adjustment. This paper provides maximum insight into when AEE(Xep) is an appropriate surrogate of AEE(X) and how to measure the difference between these two. Differential errors could be addressed and may not compromise causal inference.
The rise of new complex attacks scenarios in Internet of things (IoT) environments necessitate more advanced and intelligent cyber defense techniques such as various Intrusion Detection Systems (IDSs) which are responsible for detecting and mitigating malicious activities in IoT networks without human intervention. To address this issue, deep reinforcement learning (DRL) has been proposed in recent years, to automatically tackle intrusions/attacks. In this paper, a comprehensive survey of DRL-based IDS on IoT is presented. Furthermore, in this survey, the state-of-the-art DRL-based IDS methods have been classified into five categories including wireless sensor network (WSN), deep Q-network (DQN), healthcare, hybrid, and other techniques. In addition, the most crucial performance metrics, namely accuracy, recall, precision, false negative rate (FNR), false positive rate (FPR), and F-measure, are detailed, in order to evaluate the performance of each proposed method. The paper provides a summary of datasets utilized in the studies as well.
This paper revisits the problem of repairing and querying inconsistent databases equipped with universal constraints. We adopt symmetric difference repairs, in which both deletions and additions of facts can be used to restore consistency, and suppose that preferred repair actions are specified via a binary priority relation over (negated) facts. Our first contribution is to show how existing notions of optimal repairs, defined for simpler denial constraints and repairs solely based on fact deletion, can be suitably extended to our richer setting. We next study the computational properties of the resulting repair notions, in particular, the data complexity of repair checking and inconsistency-tolerant query answering. Finally, we clarify the relationship between optimal repairs of prioritized databases and repair notions introduced in the framework of active integrity constraints. In particular, we show that Pareto-optimal repairs in our setting correspond to founded, grounded and justified repairs w.r.t. the active integrity constraints obtained by translating the prioritized database. Our study also yields useful insights into the behavior of active integrity constraints.
Expert-designed close-ended benchmarks serve as vital tools in assessing the knowledge capacity of large language models (LLMs). Despite their widespread use, concerns have mounted regarding their reliability due to limited test scenarios and an unavoidable risk of data contamination. To rectify this, we present PertEval, a toolkit devised for in-depth probing of LLMs' knowledge capacity through knowledge-invariant perturbations. These perturbations employ human-like restatement techniques to generate on-the-fly test samples from static benchmarks, meticulously retaining knowledge-critical content while altering irrelevant details. Our toolkit further includes a suite of transition analyses that compare performance on raw vs. perturbed test sets to precisely assess LLMs' genuine knowledge capacity. Six state-of-the-art LLMs are re-evaluated using PertEval. Results reveal significantly inflated performance of the LLMs on raw benchmarks, including an absolute 21% overestimation for GPT-4. Additionally, through a nuanced response pattern analysis, we discover that PertEval retains LLMs' uncertainty to specious knowledge, potentially being resolved through rote memorization and leading to inflated performance. We also find that the detailed transition analyses by PertEval could illuminate weaknesses in existing LLMs' knowledge mastery and guide the development of refinement. Given these insights, we posit that PertEval can act as an essential tool that, when applied alongside any close-ended benchmark, unveils the true knowledge capacity of LLMs, marking a significant step toward more trustworthy LLM evaluation.
The advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of large language models has been dramatically improved, leading to human-like performances in understanding, language synthesizing, and common-sense reasoning, etc. Such a major leap-forward in general AI capacity will change the pattern of how personalization is conducted. For one thing, it will reform the way of interaction between humans and personalization systems. Instead of being a passive medium of information filtering, large language models present the foundation for active user engagement. On top of such a new foundation, user requests can be proactively explored, and user's required information can be delivered in a natural and explainable way. For another thing, it will also considerably expand the scope of personalization, making it grow from the sole function of collecting personalized information to the compound function of providing personalized services. By leveraging large language models as general-purpose interface, the personalization systems may compile user requests into plans, calls the functions of external tools to execute the plans, and integrate the tools' outputs to complete the end-to-end personalization tasks. Today, large language models are still being developed, whereas the application in personalization is largely unexplored. Therefore, we consider it to be the right time to review the challenges in personalization and the opportunities to address them with LLMs. In particular, we dedicate this perspective paper to the discussion of the following aspects: the development and challenges for the existing personalization system, the newly emerged capabilities of large language models, and the potential ways of making use of large language models for personalization.
More than one hundred benchmarks have been developed to test the commonsense knowledge and commonsense reasoning abilities of artificial intelligence (AI) systems. However, these benchmarks are often flawed and many aspects of common sense remain untested. Consequently, we do not currently have any reliable way of measuring to what extent existing AI systems have achieved these abilities. This paper surveys the development and uses of AI commonsense benchmarks. We discuss the nature of common sense; the role of common sense in AI; the goals served by constructing commonsense benchmarks; and desirable features of commonsense benchmarks. We analyze the common flaws in benchmarks, and we argue that it is worthwhile to invest the work needed ensure that benchmark examples are consistently high quality. We survey the various methods of constructing commonsense benchmarks. We enumerate 139 commonsense benchmarks that have been developed: 102 text-based, 18 image-based, 12 video based, and 7 simulated physical environments. We discuss the gaps in the existing benchmarks and aspects of commonsense reasoning that are not addressed in any existing benchmark. We conclude with a number of recommendations for future development of commonsense AI benchmarks.
Small data challenges have emerged in many learning problems, since the success of deep neural networks often relies on the availability of a huge amount of labeled data that is expensive to collect. To address it, many efforts have been made on training complex models with small data in an unsupervised and semi-supervised fashion. In this paper, we will review the recent progresses on these two major categories of methods. A wide spectrum of small data models will be categorized in a big picture, where we will show how they interplay with each other to motivate explorations of new ideas. We will review the criteria of learning the transformation equivariant, disentangled, self-supervised and semi-supervised representations, which underpin the foundations of recent developments. Many instantiations of unsupervised and semi-supervised generative models have been developed on the basis of these criteria, greatly expanding the territory of existing autoencoders, generative adversarial nets (GANs) and other deep networks by exploring the distribution of unlabeled data for more powerful representations. While we focus on the unsupervised and semi-supervised methods, we will also provide a broader review of other emerging topics, from unsupervised and semi-supervised domain adaptation to the fundamental roles of transformation equivariance and invariance in training a wide spectrum of deep networks. It is impossible for us to write an exclusive encyclopedia to include all related works. Instead, we aim at exploring the main ideas, principles and methods in this area to reveal where we are heading on the journey towards addressing the small data challenges in this big data era.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191