Some argue that the essence of humanity, such as creativity and sentiment, can never be mimicked by machines. This paper casts doubt on this belief by studying a vital question: Can AI compose poetry as well as humans? To answer the question, we propose ProFTAP, a novel evaluation framework inspired by Turing test to assess AI's poetry writing capability. We apply it on current large language models (LLMs) and find that recent LLMs do indeed possess the ability to write classical Chinese poems nearly indistinguishable from those of humans. We also reveal that various open-source LLMs can outperform GPT-4 on this task.

Conventional audio classification relied on predefined classes, lacking the ability to learn from free-form text. Recent methods unlock learning joint audio-text embeddings from raw audio-text pairs describing audio in natural language. Despite recent advancements, there is little exploration of systematic methods to train models for recognizing sound events and sources in alternative scenarios, such as distinguishing fireworks from gunshots at outdoor events in similar situations. This study introduces causal reasoning and counterfactual analysis in the audio domain. We use counterfactual instances and include them in our model across different aspects. Our model considers acoustic characteristics and sound source information from human-annotated reference texts. To validate the effectiveness of our model, we conducted pre-training utilizing multiple audio captioning datasets. We then evaluate with several common downstream tasks, demonstrating the merits of the proposed method as one of the first works leveraging counterfactual information in audio domain. Specifically, the top-1 accuracy in open-ended language-based audio retrieval task increased by more than 43%.

In-context Learning (ICL) is one of the key methods for enhancing the performance of large language models on specific tasks by providing a set of few-shot examples. However, the ICL capability of different types of models shows significant variation due to factors such as model architecture, volume of learning data, and the size of parameters. Generally, the larger the model's parameter size and the more extensive the learning data, the stronger its ICL capability. In this paper, we propose a method SLEICL that involves learning from examples using strong language models and then summarizing and transferring these learned skills to weak language models for inference and application. This ensures the stability and effectiveness of ICL. Compared to directly enabling weak language models to learn from prompt examples, SLEICL reduces the difficulty of ICL for these models. Our experiments, conducted on up to eight datasets with five language models, demonstrate that weak language models achieve consistent improvement over their own zero-shot or few-shot capabilities using the SLEICL method. Some weak language models even surpass the performance of GPT4-1106-preview (zero-shot) with the aid of SLEICL.

In past years, we have been dedicated to automating user acceptance testing (UAT) process of WeChat Pay, one of the most influential mobile payment applications in China. A system titled XUAT has been developed for this purpose. However, there is still a human-labor-intensive stage, i.e, test scripts generation, in the current system. Therefore, in this paper, we concentrate on methods of boosting the automation level of the current system, particularly the stage of test scripts generation. With recent notable successes, large language models (LLMs) demonstrate significant potential in attaining human-like intelligence and there has been a growing research area that employs LLMs as autonomous agents to obtain human-like decision-making capabilities. Inspired by these works, we propose an LLM-powered multi-agent collaborative system, named XUAT-Copilot, for automated UAT. The proposed system mainly consists of three LLM-based agents responsible for action planning, state checking and parameter selecting, respectively, and two additional modules for state sensing and case rewriting. The agents interact with testing device, make human-like decision and generate action command in a collaborative way. The proposed multi-agent system achieves a close effectiveness to human testers in our experimental studies and gains a significant improvement of Pass@1 accuracy compared with single-agent architecture. More importantly, the proposed system has launched in the formal testing environment of WeChat Pay mobile app, which saves a considerable amount of manpower in the daily development work.

Zero-shot keyphrase extraction aims to build a keyphrase extractor without training by human-annotated data, which is challenging due to the limited human intervention involved. Challenging but worthwhile, zero-shot setting efficiently reduces the time and effort that data labeling takes. Recent efforts on pre-trained large language models (e.g., ChatGPT and ChatGLM) show promising performance on zero-shot settings, thus inspiring us to explore prompt-based methods. In this paper, we ask whether strong keyphrase extraction models can be constructed by directly prompting the large language model ChatGPT. Through experimental results, it is found that ChatGPT still has a lot of room for improvement in the keyphrase extraction task compared to existing state-of-the-art unsupervised and supervised models.

Automatic extraction of information from publications is key to making scientific knowledge machine readable at a large scale. The extracted information can, for example, facilitate academic search, decision making, and knowledge graph construction. An important type of information not covered by existing approaches is hyperparameters. In this paper, we formalize and tackle hyperparameter information extraction (HyperPIE) as an entity recognition and relation extraction task. We create a labeled data set covering publications from a variety of computer science disciplines. Using this data set, we train and evaluate BERT-based fine-tuned models as well as five large language models: GPT-3.5, GALACTICA, Falcon, Vicuna, and WizardLM. For fine-tuned models, we develop a relation extraction approach that achieves an improvement of 29% F1 over a state-of-the-art baseline. For large language models, we develop an approach leveraging YAML output for structured data extraction, which achieves an average improvement of 5.5% F1 in entity recognition over using JSON. With our best performing model we extract hyperparameter information from a large number of unannotated papers, and analyze patterns across disciplines. All our data and source code is publicly available at https://github.com/IllDepence/hyperpie

Federated learning (FL) emphasizes decentralized training by storing data locally and sending only model updates, underlining user privacy. Recently, a line of works on privacy attacks impairs user privacy by extracting sensitive training text from language models in the context of FL. Yet, these attack techniques face distinct hurdles: some work chiefly with limited batch sizes (e.g., batch size of 1), and others are easily detectable. This paper introduces an innovative approach that is challenging to detect, significantly enhancing the recovery rate of text in various batch-size settings. Building on fundamental gradient matching and domain prior knowledge, we enhance the attack by recovering the input of the Pooler layer of language models, which enables us to provide additional supervised signals at the feature level. Unlike gradient data, these signals do not average across sentences and tokens, thereby offering more nuanced and effective insights. We benchmark our method using text classification tasks on datasets such as CoLA, SST-2, and Rotten Tomatoes. Across different batch sizes and models, our approach consistently outperforms previous state-of-the-art results.

Driven by curiosity, humans have continually sought to explore and understand the world around them, leading to the invention of various tools to satiate this inquisitiveness. Despite not having the capacity to process and memorize vast amounts of information in their brains, humans excel in critical thinking, planning, reflection, and harnessing available tools to interact with and interpret the world, enabling them to find answers efficiently. The recent advancements in large language models (LLMs) suggest that machines might also possess the aforementioned human-like capabilities, allowing them to exhibit powerful abilities even with a constrained parameter count. In this paper, we introduce KwaiAgents, a generalized information-seeking agent system based on LLMs. Within KwaiAgents, we propose an agent system that employs LLMs as its cognitive core, which is capable of understanding a user's query, behavior guidelines, and referencing external documents. The agent can also update and retrieve information from its internal memory, plan and execute actions using a time-aware search-browse toolkit, and ultimately provide a comprehensive response. We further investigate the system's performance when powered by LLMs less advanced than GPT-4, and introduce the Meta-Agent Tuning (MAT) framework, designed to ensure even an open-sourced 7B or 13B model performs well among many agent systems. We exploit both benchmark and human evaluations to systematically validate these capabilities. Extensive experiments show the superiority of our agent system compared to other autonomous agents and highlight the enhanced generalized agent-abilities of our fine-tuned LLMs.

Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and has been the subject of much research. Most recent works frame it as a reinforcement learning problem, where a reward function is learned from pairwise preference data and the LLM is treated as a policy which is adapted to maximize the rewards, often under additional regularization constraints. We propose an alternative interpretation which centers on the generative process for pairwise preferences and treats LHF as a density estimation problem. We provide theoretical and empirical results showing that for a family of generative processes defined via preference behavior distribution equations, training a reward function on pairwise preferences effectively models an annotator's implicit preference distribution. Finally, we discuss and present findings on "annotator misspecification" -- failure cases where wrong modeling assumptions are made about annotator behavior, resulting in poorly-adapted models -- suggesting that approaches that learn from pairwise human preferences could have trouble learning from a population of annotators with diverse viewpoints.

In-context learning (ICL) with large language models (LLMs) has become the modern tools of choice for many natural language processing tasks. However, how the text style of in-context examples influences the performance of LLMs still remains under-explored. This paper presents a novel and effective approach, named \textbf{AlignedCoT}, to improve the reasoning capability of LLMs by aligning the in-context examples with the native style of LLMs.''Native'' refers to the inherent characteristic of LLMs which can be probed by zero-shot scenarios.AlignedCoT is widely applicable to ICL methods, making it easy to combine with state-of-the-art techniques to further improve the LLMs' performance. We conduct extensive and comprehensive experiments on several benchmarks on mathematical question-answering, common-sense reasoning, and text understanding. The empirical results demonstrate that our AlignedCoT significantly improves performance over the carefully handcrafted demonstrations. Specifically, with AlignedCoT, we observe an average +3.2\% improvement for \texttt{gpt-3.5-turbo} compared to the carefully handcrafted CoT on multi-step reasoning benchmarks.Furthermore, we use AlignedCoT to rewrite the CoT text style in the training set, which improves the performance of Retrieval Augmented Generation by 3.6\%.The source code and dataset is available at https://github.com/yangzhch6/AlignedCoT