Recently, AI assistants based on large language models (LLMs) show surprising performance in many tasks, such as dialogue, solving math problems, writing code, and using tools. Although LLMs possess intensive world knowledge, they still make factual errors when facing some knowledge intensive tasks, like open-domain question answering. These untruthful responses from the AI assistant may cause significant risks in practical applications. We believe that an AI assistant's refusal to answer questions it does not know is a crucial method for reducing hallucinations and making the assistant truthful. Therefore, in this paper, we ask the question "Can AI assistants know what they don't know and express them through natural language?" To answer this question, we construct a model-specific "I don't know" (Idk) dataset for an assistant, which contains its known and unknown questions, based on existing open-domain question answering datasets. Then we align the assistant with its corresponding Idk dataset and observe whether it can refuse to answer its unknown questions after alignment. Experimental results show that after alignment with Idk datasets, the assistant can refuse to answer most its unknown questions. For questions they attempt to answer, the accuracy is significantly higher than before the alignment.

The widespread adoption of large language models (LLMs) across various regions underscores the urgent need to evaluate their alignment with human values. Current benchmarks, however, fall short of effectively uncovering safety vulnerabilities in LLMs. Despite numerous models achieving high scores and 'topping the chart' in these evaluations, there is still a significant gap in LLMs' deeper alignment with human values and achieving genuine harmlessness. To this end, this paper proposes the first highly adversarial benchmark named Flames, consisting of 2,251 manually crafted prompts, ~18.7K model responses with fine-grained annotations, and a specified scorer. Our framework encompasses both common harmlessness principles, such as fairness, safety, legality, and data protection, and a unique morality dimension that integrates specific Chinese values such as harmony. Based on the framework, we carefully design adversarial prompts that incorporate complex scenarios and jailbreaking methods, mostly with implicit malice. By prompting mainstream LLMs with such adversarially constructed prompts, we obtain model responses, which are then rigorously annotated for evaluation. Our findings indicate that all the evaluated LLMs demonstrate relatively poor performance on Flames, particularly in the safety and fairness dimensions. Claude emerges as the best-performing model overall, but with its harmless rate being only 63.08% while GPT-4 only scores 39.04%. The complexity of Flames has far exceeded existing benchmarks, setting a new challenge for contemporary LLMs and highlighting the need for further alignment of LLMs. To efficiently evaluate new models on the benchmark, we develop a specified scorer capable of scoring LLMs across multiple dimensions, achieving an accuracy of 77.4%. The Flames Benchmark is publicly available on https://github.com/AIFlames/Flames.

In this paper, we establish a benchmark named HalluQA (Chinese Hallucination Question-Answering) to measure the hallucination phenomenon in Chinese large language models. HalluQA contains 450 meticulously designed adversarial questions, spanning multiple domains, and takes into account Chinese historical culture, customs, and social phenomena. During the construction of HalluQA, we consider two types of hallucinations: imitative falsehoods and factual errors, and we construct adversarial samples based on GLM-130B and ChatGPT. For evaluation, we design an automated evaluation method using GPT-4 to judge whether a model output is hallucinated. We conduct extensive experiments on 24 large language models, including ERNIE-Bot, Baichuan2, ChatGLM, Qwen, SparkDesk and etc. Out of the 24 models, 18 achieved non-hallucination rates lower than 50%. This indicates that HalluQA is highly challenging. We analyze the primary types of hallucinations in different types of models and their causes. Additionally, we discuss which types of hallucinations should be prioritized for different types of models.

For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are artificial entities that sense their environment, make decisions, and take actions. Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks. Actually, what the community lacks is a general and powerful model to serve as a starting point for designing AI agents that can adapt to diverse scenarios. Due to the versatile capabilities they demonstrate, large language models (LLMs) are regarded as potential sparks for Artificial General Intelligence (AGI), offering hope for building general AI agents. Many researchers have leveraged LLMs as the foundation to build AI agents and have achieved significant progress. In this paper, we perform a comprehensive survey on LLM-based agents. We start by tracing the concept of agents from its philosophical origins to its development in AI, and explain why LLMs are suitable foundations for agents. Building upon this, we present a general framework for LLM-based agents, comprising three main components: brain, perception, and action, and the framework can be tailored for different applications. Subsequently, we explore the extensive applications of LLM-based agents in three aspects: single-agent scenarios, multi-agent scenarios, and human-agent cooperation. Following this, we delve into agent societies, exploring the behavior and personality of LLM-based agents, the social phenomena that emerge from an agent society, and the insights they offer for human society. Finally, we discuss several key topics and open problems within the field. A repository for the related papers at https://github.com/WooooDyy/LLM-Agent-Paper-List.

Automated machine learning (AutoML) seeks to build ML models with minimal human effort. While considerable research has been conducted in the area of AutoML in general, aiming to take humans out of the loop when building artificial intelligence (AI) applications, scant literature has focused on how AutoML works well in open-environment scenarios such as the process of training and updating large models, industrial supply chains or the industrial metaverse, where people often face open-loop problems during the search process: they must continuously collect data, update data and models, satisfy the requirements of the development and deployment environment, support massive devices, modify evaluation metrics, etc. Addressing the open-environment issue with pure data-driven approaches requires considerable data, computing resources, and effort from dedicated data engineers, making current AutoML systems and platforms inefficient and computationally intractable. Human-computer interaction is a practical and feasible way to tackle the problem of open-environment AI. In this paper, we introduce OmniForce, a human-centered AutoML (HAML) system that yields both human-assisted ML and ML-assisted human techniques, to put an AutoML system into practice and build adaptive AI in open-environment scenarios. Specifically, we present OmniForce in terms of ML version management; pipeline-driven development and deployment collaborations; a flexible search strategy framework; and widely provisioned and crowdsourced application algorithms, including large models. Furthermore, the (large) models constructed by OmniForce can be automatically turned into remote services in a few minutes; this process is dubbed model as a service (MaaS). Experimental results obtained in multiple search spaces and real-world use cases demonstrate the efficacy and efficiency of OmniForce.

We investigate how to enhance answer precision in frequently asked questions posed by distributed users using cloud-based Large Language Models (LLMs). Our study focuses on a typical situations where users ask similar queries that involve identical mathematical reasoning steps and problem-solving procedures. Due to the unsatisfactory accuracy of LLMs' zero-shot prompting with standalone questions, we propose to improve the distributed synonymous questions using Self-Consistency (SC) and Chain-of-Thought (CoT) techniques. Specifically, we first retrieve synonymous questions from a crowd-sourced database and create a federated question pool. We call these federated synonymous questions with the same or different parameters SP-questions or DP-questions, respectively. We refer to our methods as Fed-SP-SC and Fed-DP-CoT, which can generate significantly more accurate answers for all user queries without requiring sophisticated model-tuning. Through extensive experiments, we demonstrate that our proposed methods can significantly enhance question accuracy by fully exploring the synonymous nature of the questions and the consistency of the answers.

Supersized pre-trained language models have pushed the accuracy of various NLP tasks to a new state-of-the-art (SOTA). Rather than pursuing the reachless SOTA accuracy, most works are pursuing improvement on other dimensions such as efficiency, leading to "Pareto SOTA". Different from accuracy, the metric for efficiency varies across different studies, making them hard to be fairly compared. To that end, this work presents ELUE (Efficient Language Understanding Evaluation), a standard evaluation, and a public leaderboard for efficient NLP models. ELUE is dedicated to depicting the Pareto Front for various language understanding tasks, such that it can tell whether and how much a method achieves Pareto improvement. Along with the benchmark, we also pre-train and release a strong baseline, ElasticBERT, whose elasticity is both static and dynamic. ElasticBERT is static in that it allows reducing model layers on demand. ElasticBERT is dynamic in that it selectively executes parts of model layers conditioned on the input. We demonstrate the ElasticBERT, despite its simplicity, outperforms or performs on par with SOTA compressed and early exiting models. The ELUE benchmark is publicly available at http://eluebenchmark.fastnlp.top/.

In the era of deep learning, modeling for most NLP tasks has converged to several mainstream paradigms. For example, we usually adopt the sequence labeling paradigm to solve a bundle of tasks such as POS-tagging, NER, Chunking, and adopt the classification paradigm to solve tasks like sentiment analysis. With the rapid progress of pre-trained language models, recent years have observed a rising trend of Paradigm Shift, which is solving one NLP task by reformulating it as another one. Paradigm shift has achieved great success on many tasks, becoming a promising way to improve model performance. Moreover, some of these paradigms have shown great potential to unify a large number of NLP tasks, making it possible to build a single model to handle diverse tasks. In this paper, we review such phenomenon of paradigm shifts in recent years, highlighting several paradigms that have the potential to solve different NLP tasks.

Transformers have achieved great success in many artificial intelligence fields, such as natural language processing, computer vision, and audio processing. Therefore, it is natural to attract lots of interest from academic and industry researchers. Up to the present, a great variety of Transformer variants (a.k.a. X-formers) have been proposed, however, a systematic and comprehensive literature review on these Transformer variants is still missing. In this survey, we provide a comprehensive review of various X-formers. We first briefly introduce the vanilla Transformer and then propose a new taxonomy of X-formers. Next, we introduce the various X-formers from three perspectives: architectural modification, pre-training, and applications. Finally, we outline some potential directions for future research.

In modern data science problems, techniques for extracting value from big data require performing large-scale optimization over heterogenous, irregularly structured data. Much of this data is best represented as multi-relational graphs, making vertex programming abstractions such as those of Pregel and GraphLab ideal fits for modern large-scale data analysis. In this paper, we describe a vertex-programming implementation of a popular consensus optimization technique known as the alternating direction of multipliers (ADMM). ADMM consensus optimization allows elegant solution of complex objectives such as inference in rich probabilistic models. We also introduce a novel hypergraph partitioning technique that improves over state-of-the-art partitioning techniques for vertex programming and significantly reduces the communication cost by reducing the number of replicated nodes up to an order of magnitude. We implemented our algorithm in GraphLab and measure scaling performance on a variety of realistic bipartite graph distributions and a large synthetic voter-opinion analysis application. In our experiments, we are able to achieve a 50% improvement in runtime over the current state-of-the-art GraphLab partitioning scheme.