Existing open-source helpfulness preference datasets do not specify what makes some responses more helpful and others less so. Models trained on these datasets can incidentally learn to model dataset artifacts (e.g. preferring longer but unhelpful responses only due to their length). To alleviate this problem, we collect HelpSteer, a multi-attribute helpfulness dataset annotated for the various aspects that make responses helpful. Specifically, our 37k-sample dataset has annotations for correctness, coherence, complexity, and verbosity in addition to overall helpfulness of responses. Training Llama 2 70B using the HelpSteer dataset with SteerLM technique produces a model that scores 7.54 on MT Bench, which is currently the highest score for open models that do not require training data from more powerful models (e.g. GPT4). We release this dataset with CC-BY-4.0 license at https://huggingface.co/datasets/nvidia/HelpSteer
Just as computational simulations of atoms, molecules and cells have shaped the way we study the sciences, true-to-life simulations of human-like agents can be valuable tools for studying human behavior. We propose Humanoid Agents, a system that guides Generative Agents to behave more like humans by introducing three elements of System 1 processing: Basic needs (e.g. hunger, health and energy), Emotion and Closeness in Relationships. Humanoid Agents are able to use these dynamic elements to adapt their daily activities and conversations with other agents, as supported with empirical experiments. Our system is designed to be extensible to various settings, three of which we demonstrate, as well as to other elements influencing human behavior (e.g. empathy, moral values and cultural background). Our platform also includes a Unity WebGL game interface for visualization and an interactive analytics dashboard to show agent statuses over time. Our platform is available on https://www.humanoidagents.com/ and code is on https://github.com/HumanoidAgents/HumanoidAgents
Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) stages. However, RLHF faces inherent limitations stemming from a complex training setup and its tendency to align the model with implicit values that end users cannot control at run-time. Moreover, reward models in RLHF stage commonly rely on single-dimensional feedback as opposed to explicit, multifaceted signals that indicate attributes such as helpfulness, humor, and toxicity. To address these limitations, we propose SteerLM, a supervised fine-tuning method that empowers end-users to control responses during inference. SteerLM conditions responses to conform to an explicitly defined multi-dimensional set of attributes, thereby empowering a steerable AI capable of generating helpful and high-quality responses while maintaining customizability. Experiments show that SteerLM trained on open source datasets generates responses that are preferred by human and automatic evaluators to many state-of-the-art baselines trained with RLHF while being much easier to train. Try SteerLM at https://huggingface.co/nvidia/SteerLM-llama2-13B
The widely used Fact-based Visual Question Answering (FVQA) dataset contains visually-grounded questions that require information retrieval using common sense knowledge graphs to answer. It has been observed that the original dataset is highly imbalanced and concentrated on a small portion of its associated knowledge graph. We introduce FVQA 2.0 which contains adversarial variants of test questions to address this imbalance. We show that systems trained with the original FVQA train sets can be vulnerable to adversarial samples and we demonstrate an augmentation scheme to reduce this vulnerability without human annotations.
Knowledge graph (KG) based Collaborative Filtering is an effective approach to personalizing recommendation systems for relatively static domains such as movies and books, by leveraging structured information from KG to enrich both item and user representations. Motivated by the use of Transformers for understanding rich text in content-based filtering recommender systems, we propose Content-aware KG-enhanced Meta-preference Networks as a way to enhance collaborative filtering recommendation based on both structured information from KG as well as unstructured content features based on Transformer-empowered content-based filtering. To achieve this, we employ a novel training scheme, Cross-System Contrastive Learning, to address the inconsistency of the two very different systems and propose a powerful collaborative filtering model and a variant of the well-known NRMS system within this modeling framework. We also contribute to public domain resources through the creation of a large-scale movie-knowledge-graph dataset and an extension of the already public Amazon-Book dataset through incorporation of text descriptions crawled from external sources. We present experimental results showing that enhancing collaborative filtering with Transformer-based features derived from content-based filtering outperforms strong baseline systems, improving the ability of knowledge-graph-based collaborative filtering systems to exploit item content information.
Blockchain-based federated learning (BCFL) has recently gained tremendous attention because of its advantages such as decentralization and privacy protection of raw data. However, there has been few research focusing on the allocation of resources for clients in BCFL. In the BCFL framework where the FL clients and the blockchain miners are the same devices, clients broadcast the trained model updates to the blockchain network and then perform mining to generate new blocks. Since each client has a limited amount of computing resources, the problem of allocating computing resources into training and mining needs to be carefully addressed. In this paper, we design an incentive mechanism to assign each client appropriate rewards for training and mining, and then the client will determine the amount of computing power to allocate for each subtask based on these rewards using the two-stage Stackelberg game. After analyzing the utilities of the model owner (MO) (i.e., the BCFL task publisher) and clients, we transform the game model into two optimization problems, which are sequentially solved to derive the optimal strategies for both the MO and clients. Further, considering the fact that local training related information of each client may not be known by others, we extend the game model with analytical solutions to the incomplete information scenario. Extensive experimental results demonstrate the validity of our proposed schemes.
Mobile crowdsensing (MCS) counting on the mobility of massive workers helps the requestor accomplish various sensing tasks with more flexibility and lower cost. However, for the conventional MCS, the large consumption of communication resources for raw data transmission and high requirements on data storage and computing capability hinder potential requestors with limited resources from using MCS. To facilitate the widespread application of MCS, we propose a novel MCS learning framework leveraging on blockchain technology and the new concept of edge intelligence based on federated learning (FL), which involves four major entities, including requestors, blockchain, edge servers and mobile devices as workers. Even though there exist several studies on blockchain-based MCS and blockchain-based FL, they cannot solve the essential challenges of MCS with respect to accommodating resource-constrained requestors or deal with the privacy concerns brought by the involvement of requestors and workers in the learning process. To fill the gaps, four main procedures, i.e., task publication, data sensing and submission, learning to return final results, and payment settlement and allocation, are designed to address major challenges brought by both internal and external threats, such as malicious edge servers and dishonest requestors. Specifically, a mechanism design based data submission rule is proposed to guarantee the data privacy of mobile devices being truthfully preserved at edge servers; consortium blockchain based FL is elaborated to secure the distributed learning process; and a cooperation-enforcing control strategy is devised to elicit full payment from the requestor. Extensive simulations are carried out to evaluate the performance of our designed schemes.
With the technological advances in machine learning, effective ways are available to process the huge amount of data generated in real life. However, issues of privacy and scalability will constrain the development of machine learning. Federated learning (FL) can prevent privacy leakage by assigning training tasks to multiple clients, thus separating the central server from the local devices. However, FL still suffers from shortcomings such as single-point-failure and malicious data. The emergence of blockchain provides a secure and efficient solution for the deployment of FL. In this paper, we conduct a comprehensive survey of the literature on blockchained FL (BCFL). First, we investigate how blockchain can be applied to federal learning from the perspective of system composition. Then, we analyze the concrete functions of BCFL from the perspective of mechanism design and illustrate what problems blockchain addresses specifically for FL. We also survey the applications of BCFL in reality. Finally, we discuss some challenges and future research directions.
Personal attributes represent structured information about a person, such as their hobbies, pets, family, likes and dislikes. In this work, we introduce the tasks of extracting and inferring personal attributes from human-human dialogue. We first demonstrate the benefit of incorporating personal attributes in a social chit-chat dialogue model and task-oriented dialogue setting. Thus motivated, we propose the tasks of personal attribute extraction and inference, and then analyze the linguistic demands of these tasks. To meet these challenges, we introduce a simple and extensible model that combines an autoregressive language model utilizing constrained attribute generation with a discriminative reranker. Our model outperforms strong baselines on extracting personal attributes as well as inferring personal attributes that are not contained verbatim in utterances and instead requires commonsense reasoning and lexical inferences, which occur frequently in everyday conversation.
Identifying similar movie characters is a captivating task that can be our first step to understand the commonalities between human characteristics and experiences. Here, we seek to identify similar movie character descriptions and evaluate our findings based on whether they belong to a common fan-curated trope (theme). Rather than simply comparing the embedding representation of character description, we use a pair-wise attention model to make use of complex word/span-level relationships across the two character descriptions to predict the similarity of the two characters. Naively, such a model would require the exhaustive comparison of each character to all other characters, which is an O(n^2) operation with respect to the number of characters, making it unfeasible to be used in practice. We reduced this into an O(n) operation using a two-step approach that involves choosing only a tiny fraction of character-pairs to perform pairwise attention on while still being effective in this task. Our approach performs at least 9-27% better than methods based on state-of-the-art paragraph embedding representations.