As the latest advancements in natural language processing, large language models (LLMs) have achieved human-level language understanding and generation abilities in many real-world tasks, and even have been regarded as a potential path to the artificial general intelligence. To better facilitate research on LLMs, many open-source LLMs, such as Llama 2 and Falcon, have recently been proposed and gained comparable performances to proprietary models. However, these models are primarily designed for English scenarios and exhibit poor performances in Chinese contexts. In this technical report, we propose YAYI 2, including both base and chat models, with 30 billion parameters. YAYI 2 is pre-trained from scratch on a multilingual corpus which contains 2.65 trillion tokens filtered by our pre-training data processing pipeline. The base model is aligned with human values through supervised fine-tuning with millions of instructions and reinforcement learning from human feedback. Extensive experiments on multiple benchmarks, such as MMLU and CMMLU, consistently demonstrate that the proposed YAYI 2 outperforms other similar sized open-source models.
E-commerce pre-sales dialogue aims to understand and elicit user needs and preferences for the items they are seeking so as to provide appropriate recommendations. Conversational recommender systems (CRSs) learn user representation and provide accurate recommendations based on dialogue context, but rely on external knowledge. Large language models (LLMs) generate responses that mimic pre-sales dialogues after fine-tuning, but lack domain-specific knowledge for accurate recommendations. Intuitively, the strengths of LLM and CRS in E-commerce pre-sales dialogues are complementary, yet no previous work has explored this. This paper investigates the effectiveness of combining LLM and CRS in E-commerce pre-sales dialogues, proposing two collaboration methods: CRS assisting LLM and LLM assisting CRS. We conduct extensive experiments on a real-world dataset of Ecommerce pre-sales dialogues. We analyze the impact of two collaborative approaches with two CRSs and two LLMs on four tasks of Ecommerce pre-sales dialogue. We find that collaborations between CRS and LLM can be very effective in some cases.
In many reinforcement learning tasks, the agent has to learn to interact with many objects of different types and generalize to unseen combinations and numbers of objects. Often a task is a composition of previously learned tasks (e.g. block stacking). These are examples of compositional generalization, in which we compose object-centric representations to solve complex tasks. Recent works have shown the benefits of object-factored representations and hierarchical abstractions for improving sample efficiency in these settings. On the other hand, these methods do not fully exploit the benefits of factorization in terms of object attributes. In this paper, we address this opportunity and introduce the Dynamic Attribute FacTored RL (DAFT-RL) framework. In DAFT-RL, we leverage object-centric representation learning to extract objects from visual inputs. We learn to classify them in classes and infer their latent parameters. For each class of object, we learn a class template graph that describes how the dynamics and reward of an object of this class factorize according to its attributes. We also learn an interaction pattern graph that describes how objects of different classes interact with each other at the attribute level. Through these graphs and a dynamic interaction graph that models the interactions between objects, we can learn a policy that can then be directly applied in a new environment by just estimating the interactions and latent parameters. We evaluate DAFT-RL in three benchmark datasets and show our framework outperforms the state-of-the-art in generalizing across unseen objects with varying attributes and latent parameters, as well as in the composition of previously learned tasks.
Conversational recommender systems (CRSs) aim to understand the information needs and preferences expressed in a dialogue to recommend suitable items to the user. Most of the existing conversational recommendation datasets are synthesized or simulated with crowdsourcing, which has a large gap with real-world scenarios. To bridge the gap, previous work contributes a dataset E-ConvRec, based on pre-sales dialogues between users and customer service staff in E-commerce scenarios. However, E-ConvRec only supplies coarse-grained annotations and general tasks for making recommendations in pre-sales dialogues. Different from that, we use real user needs as a clue to explore the E-commerce conversational recommendation in complex pre-sales dialogues, namely user needs-centric E-commerce conversational recommendation (UNECR). In this paper, we construct a user needs-centric E-commerce conversational recommendation dataset (U-NEED) from real-world E-commerce scenarios. U-NEED consists of 3 types of resources: (i) 7,698 fine-grained annotated pre-sales dialogues in 5 top categories (ii) 333,879 user behaviors and (iii) 332,148 product knowledge tuples. To facilitate the research of UNECR, we propose 5 critical tasks: (i) pre-sales dialogue understanding (ii) user needs elicitation (iii) user needs-based recommendation (iv) pre-sales dialogue generation and (v) pre-sales dialogue evaluation. We establish baseline methods and evaluation metrics for each task. We report experimental results of 5 tasks on U-NEED. We also report results in 3 typical categories. Experimental results indicate that the challenges of UNECR in various categories are different.
With the capacity of continual learning, humans can continuously acquire knowledge throughout their lifespan. However, computational systems are not, in general, capable of learning tasks sequentially. This long-standing challenge for deep neural networks (DNNs) is called catastrophic forgetting. Multiple solutions have been proposed to overcome this limitation. This paper makes an in-depth evaluation of the memory replay methods, exploring the efficiency, performance, and scalability of various sampling strategies when selecting replay data. All experiments are conducted on multiple datasets under various domains. Finally, a practical solution for selecting replay methods for various data distributions is provided.
Dealing with non-stationarity in environments (i.e., transition dynamics) and objectives (i.e., reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL). Most existing approaches only focus on families of stationary MDPs, in which the non-stationarity is episodic, i.e., the change is only possible across episodes. The few works that do consider non-stationarity without a specific boundary, i.e., also allow for changes within an episode, model the changes monolithically in a single shared embedding vector. In this paper, we propose Factored Adaptation for Non-Stationary RL (FANS-RL), a factored adaption approach that explicitly learns the individual latent change factors affecting the transition dynamics and reward functions. FANS-RL learns jointly the structure of a factored MDP and a factored representation of the time-varying change factors, as well as the specific state components that they affect, via a factored non-stationary variational autoencoder. Through this general framework, we can consider general non-stationary scenarios with different changing function types and changing frequency. Experimental results demonstrate that FANS-RL outperforms existing approaches in terms of rewards, compactness of the latent state representation and robustness to varying degrees of non-stationarity.
Acoustic and visual sensing can support the contactless estimation of the weight of a container and the amount of its content when the container is manipulated by a person. However, transparencies (both of the container and of the content) and the variability of materials, shapes and sizes make this problem challenging. In this paper, we present an open benchmarking framework and an in-depth comparative analysis of recent methods that estimate the capacity of a container, as well as the type, mass, and amount of its content. These methods use learned and handcrafted features, such as mel-frequency cepstrum coefficients, zero-crossing rate, spectrograms, with different types of classifiers to estimate the type and amount of the content with acoustic data, and geometric approaches with visual data to determine the capacity of the container. Results on a newly distributed dataset show that audio alone is a strong modality and methods achieves a weighted average F1-score up to 81% and 97% for content type and level classification, respectively. Estimating the container capacity with vision-only approaches and filling mass with multi-modal, multi-stage algorithms reaches up to 65% weighted average capacity and mass scores.
Most approaches in reinforcement learning (RL) are data-hungry and specific to fixed environments. In this paper, we propose a principled framework for adaptive RL, called AdaRL, that adapts reliably to changes across domains. Specifically, we construct a generative environment model for the structural relationships among variables in the system and embed the changes in a compact way, which provides a clear and interpretable picture for locating what and where the changes are and how to adapt. Based on the environment model, we characterize a minimal set of representations, including both domain-specific factors and domain-shared state representations, that suffice for reliable and low-cost transfer. Moreover, we show that by explicitly leveraging a compact representation to encode changes, we can adapt the policy with only a few samples without further policy optimization in the target domain. We illustrate the efficacy of AdaRL through a series of experiments that allow for changes in different components of Cartpole and Atari games.
Empirical mode decomposition (EMD) has developed into a prominent tool for adaptive, scale-based signal analysis in various fields like robotics, security and biomedical engineering. Since the dramatic increase in amount of data puts forward higher requirements for the capability of real-time signal analysis, it is difficult for existing EMD and its variants to trade off the growth of data dimension and the speed of signal analysis. In order to decompose multi-dimensional signals at a faster speed, we present a novel signal-serialization method (serial-EMD), which concatenates multi-variate or multi-dimensional signals into a one-dimensional signal and uses various one-dimensional EMD algorithms to decompose it. To verify the effects of the proposed method, synthetic multi-variate time series, artificial 2D images with various textures and real-world facial images are tested. Compared with existing multi-EMD algorithms, the decomposition time becomes significantly reduced. In addition, the results of facial recognition with Intrinsic Mode Functions (IMFs) extracted using our method can achieve a higher accuracy than those obtained by existing multi-EMD algorithms, which demonstrates the superior performance of our method in terms of the quality of IMFs. Furthermore, this method can provide a new perspective to optimize the existing EMD algorithms, that is, transforming the structure of the input signal rather than being constrained by developing envelope computation techniques or signal decomposition methods. In summary, the study suggests that the serial-EMD technique is a highly competitive and fast alternative for multi-dimensional signal analysis.
Conversational Recommender Systems (CRSs) in E-commerce platforms aim to recommend items to users via multiple conversational interactions. Click-through rate (CTR) prediction models are commonly used for ranking candidate items. However, most CRSs are suffer from the problem of data scarcity and sparseness. To address this issue, we propose a novel knowledge-enhanced deep cross network (K-DCN), a two-step (pretrain and fine-tune) CTR prediction model to recommend items. We first construct a billion-scale conversation knowledge graph (CKG) from information about users, items and conversations, and then pretrain CKG by introducing knowledge graph embedding method and graph convolution network to encode semantic and structural information respectively.To make the CTR prediction model sensible of current state of users and the relationship between dialogues and items, we introduce user-state and dialogue-interaction representations based on pre-trained CKG and propose K-DCN.In K-DCN, we fuse the user-state representation, dialogue-interaction representation and other normal feature representations via deep cross network, which will give the rank of candidate items to be recommended.We experimentally prove that our proposal significantly outperforms baselines and show it's real application in Alime.