The success of Reinforcement Learning from Human Feedback (RLHF) in language model alignment is critically dependent on the capability of the reward model (RM). However, as the training process progresses, the output distribution of the policy model shifts, leading to the RM's reduced ability to distinguish between responses. This issue is further compounded when the RM, trained on a specific data distribution, struggles to generalize to examples outside of that distribution. These two issues can be united as a challenge posed by the shifted distribution of the environment. To surmount this challenge, we introduce MetaRM, a method leveraging meta-learning to align the RM with the shifted environment distribution. MetaRM is designed to train the RM by minimizing data loss, particularly for data that can improve the differentiation ability to examples of the shifted target distribution. Extensive experiments demonstrate that MetaRM significantly improves the RM's distinguishing ability in iterative RLHF optimization, and also provides the capacity to identify subtle differences in out-of-distribution samples.
In recent years, multi-agent reinforcement learning algorithms have made significant advancements in diverse gaming environments, leading to increased interest in the broader application of such techniques. To address the prevalent challenge of partial observability, communication-based algorithms have improved cooperative performance through the sharing of numerical embedding between agents. However, the understanding of the formation of collaborative mechanisms is still very limited, making designing a human-understandable communication mechanism a valuable problem to address. In this paper, we propose a novel multi-agent reinforcement learning algorithm that embeds large language models into agents, endowing them with the ability to generate human-understandable verbal communication. The entire framework has a message module and an action module. The message module is responsible for generating and sending verbal messages to other agents, effectively enhancing information sharing among agents. To further enhance the message module, we employ a teacher model to generate message labels from the global view and update the student model through Supervised Fine-Tuning (SFT). The action module receives messages from other agents and selects actions based on current local observations and received messages. Experiments conducted on the Overcooked game demonstrate our method significantly enhances the learning efficiency and performance of existing methods, while also providing an interpretable tool for humans to understand the process of multi-agent cooperation.
Stance detection seeks to identify the viewpoints of individuals either in favor or against a given target or a controversial topic. Current advanced neural models for stance detection typically employ fully parametric softmax classifiers. However, these methods suffer from several limitations, including lack of explainability, insensitivity to the latent data structure, and unimodality, which greatly restrict their performance and applications. To address these challenges, we present a novel collaborative stance detection framework called (CoSD) which leverages contrastive heterogeneous topic graph learning to learn topic-aware semantics and collaborative signals among texts, topics, and stance labels for enhancing stance detection. During training, we construct a heterogeneous graph to structurally organize texts and stances through implicit topics via employing latent Dirichlet allocation. We then perform contrastive graph learning to learn heterogeneous node representations, aggregating informative multi-hop collaborative signals via an elaborate Collaboration Propagation Aggregation (CPA) module. During inference, we introduce a hybrid similarity scoring module to enable the comprehensive incorporation of topic-aware semantics and collaborative signals for stance detection. Extensive experiments on two benchmark datasets demonstrate the state-of-the-art detection performance of CoSD, verifying the effectiveness and explainability of our collaborative framework.
Decoding visual information from human brain activity has seen remarkable advancements in recent research. However, due to the significant variability in cortical parcellation and cognition patterns across subjects, current approaches personalized deep models for each subject, constraining the practicality of this technology in real-world contexts. To tackle the challenges, we introduce Wills Aligner, a robust multi-subject brain representation learner. Our Wills Aligner initially aligns different subjects' brains at the anatomical level. Subsequently, it incorporates a mixture of brain experts to learn individual cognition patterns. Additionally, it decouples the multi-subject learning task into a two-stage training, propelling the deep model and its plugin network to learn inter-subject commonality knowledge and various cognition patterns, respectively. Wills Aligner enables us to overcome anatomical differences and to efficiently leverage a single model for multi-subject brain representation learning. We meticulously evaluate the performance of our approach across coarse-grained and fine-grained visual decoding tasks. The experimental results demonstrate that our Wills Aligner achieves state-of-the-art performance.
Decoding natural visual scenes from brain activity has flourished, with extensive research in single-subject tasks and, however, less in cross-subject tasks. Reconstructing high-quality images in cross-subject tasks is a challenging problem due to profound individual differences between subjects and the scarcity of data annotation. In this work, we proposed MindTuner for cross-subject visual decoding, which achieves high-quality and rich-semantic reconstructions using only 1 hour of fMRI training data benefiting from the phenomena of visual fingerprint in the human visual system and a novel fMRI-to-text alignment paradigm. Firstly, we pre-train a multi-subject model among 7 subjects and fine-tune it with scarce data on new subjects, where LoRAs with Skip-LoRAs are utilized to learn the visual fingerprint. Then, we take the image modality as the intermediate pivot modality to achieve fMRI-to-text alignment, which achieves impressive fMRI-to-text retrieval performance and corrects fMRI-to-image reconstruction with fine-tuned semantics. The results of both qualitative and quantitative analyses demonstrate that MindTuner surpasses state-of-the-art cross-subject visual decoding models on the Natural Scenes Dataset (NSD), whether using training data of 1 hour or 40 hours.
Multimodal Sentiment Analysis (MSA) aims to identify speakers' sentiment tendencies in multimodal video content, raising serious concerns about privacy risks associated with multimodal data, such as voiceprints and facial images. Recent distributed collaborative learning has been verified as an effective paradigm for privacy preservation in multimodal tasks. However, they often overlook the privacy distinctions among different modalities, struggling to strike a balance between performance and privacy preservation. Consequently, it poses an intriguing question of maximizing multimodal utilization to improve performance while simultaneously protecting necessary modalities. This paper forms the first attempt at modality-specified (i.e., audio and visual) privacy preservation in MSA tasks. We propose a novel Hybrid Distributed cross-modality cGAN framework (HyDiscGAN), which learns multimodality alignment to generate fake audio and visual features conditioned on shareable de-identified textual data. The objective is to leverage the fake features to approximate real audio and visual content to guarantee privacy preservation while effectively enhancing performance. Extensive experiments show that compared with the state-of-the-art MSA model, HyDiscGAN can achieve superior or competitive performance while preserving privacy.
Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers without position encodings (NoPE) provides a new way to overcome the challenge. In this paper, we study the length generalization property of NoPE. We find that although NoPE can extend to longer sequences than the commonly used explicit position encodings, it still has a limited context length. We identify a connection between the failure of NoPE's generalization and the distraction of attention distributions. We propose a parameter-efficient tuning for searching attention heads' best temperature hyper-parameters, which substantially expands NoPE's context size. Experiments on long sequence language modeling, the synthetic passkey retrieval task and real-world long context tasks show that NoPE can achieve competitive performances with state-of-the-art length generalization algorithms. The source code is publicly accessible
The open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. This includes both base models, which are pre-trained on extensive datasets without alignment, and aligned models, deliberately designed to align with ethical standards and human values. Contrary to the prevalent assumption that the inherent instruction-following limitations of base LLMs serve as a safeguard against misuse, our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions. To systematically assess these risks, we introduce a novel set of risk evaluation metrics. Empirical results reveal that the outputs from base LLMs can exhibit risk levels on par with those of models fine-tuned for malicious purposes. This vulnerability, requiring neither specialized knowledge nor training, can be manipulated by almost anyone, highlighting the substantial risk and the critical need for immediate attention to the base LLMs' security protocols.
Alkaline Water Electrolysis (AWE) is one of the simplest green hydrogen production method using renewable energy. AWE system typically yields process variables that are serially correlated and contaminated by measurement uncertainty. A novel robust dynamic variational Bayesian dictionary learning (RDVDL) monitoring approach is proposed to improve the reliability and safety of AWE operation. RDVDL employs a sparse Bayesian dictionary learning to preserve the dynamic mechanism information of AWE process which allows the easy interpretation of fault detection results. To improve the robustness to measurement uncertainty, a low-rank vector autoregressive (VAR) method is derived to reliably extract the serial correlation from process variables. The effectiveness of the proposed approach is demonstrated with an industrial hydrogen production process, and RDVDL can efficiently detect and diagnose critical AWE faults.
The accuracy of the underlying model predictions is crucial for the success of model predictive control (MPC) applications. If the model is unable to accurately analyze the dynamics of the controlled system, the performance and stability guarantees provided by MPC may not be achieved. Learning-based MPC can learn models from data, improving the applicability and reliability of MPC. This study develops a nonlinear sparse variational Bayesian learning based MPC (NSVB-MPC) for nonlinear systems, where the model is learned by the developed NSVB method. Variational inference is used by NSVB-MPC to assess the predictive accuracy and make the necessary corrections to quantify system uncertainty. The suggested approach ensures input-to-state (ISS) and the feasibility of recursive constraints in accordance with the concept of an invariant terminal region. Finally, a PEMFC temperature control model experiment confirms the effectiveness of the NSVB-MPC method.