Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game

Large language models (LLMs) have exhibited memorable strategic behaviors in social deductive games. However, the significance of opinion leadership exhibited by LLM-based agents has been overlooked, which is crucial for practical applications in multi-agent and human-AI interaction settings. Opinion leaders are individuals who have a noticeable impact on the beliefs and behaviors of others within a social group. In this work, we employ the Werewolf game as a simulation platform to assess the opinion leadership of LLMs. The game features the role of the Sheriff, tasked with summarizing arguments and recommending decision options, and therefore serves as a credible proxy for an opinion leader. We develop a framework integrating the Sheriff role and devise two novel metrics for evaluation based on the critical characteristics of opinion leaders. The first metric measures the reliability of the opinion leader, and the second assesses the influence of the opinion leader on other players' decisions. We conduct extensive experiments to evaluate LLMs of different scales. In addition, we collect a Werewolf question-answering dataset (WWQA) to assess and enhance LLM's grasp of the game rules, and we also incorporate human participants for further analysis. The results suggest that the Werewolf game is a suitable test bed to evaluate the opinion leadership of LLMs and few LLMs possess the capacity for opinion leadership.

Conjugate-Gradient-like Based Adaptive Moment Estimation Optimization Algorithm for Deep Learning

Training deep neural networks is a challenging task. In order to speed up training and enhance the performance of deep neural networks, we rectify the vanilla conjugate gradient as conjugate-gradient-like and incorporate it into the generic Adam, and thus propose a new optimization algorithm named CG-like-Adam for deep learning. Specifically, both the first-order and the second-order moment estimation of generic Adam are replaced by the conjugate-gradient-like. Convergence analysis handles the cases where the exponential moving average coefficient of the first-order moment estimation is constant and the first-order moment estimation is unbiased. Numerical experiments show the superiority of the proposed algorithm based on the CIFAR10/100 dataset.

CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Re-Identification

Weakly supervised text-based person re-identification (TPRe-ID) seeks to retrieve images of a target person using textual descriptions, without relying on identity annotations and is more challenging and practical. The primary challenge is the intra-class differences, encompassing intra-modal feature variations and cross-modal semantic gaps. Prior works have focused on instance-level samples and ignored prototypical features of each person which are intrinsic and invariant. Toward this, we propose a Cross-Modal Prototypical Contrastive Learning (CPCL) method. In practice, the CPCL introduces the CLIP model to weakly supervised TPRe-ID for the first time, mapping visual and textual instances into a shared latent space. Subsequently, the proposed Prototypical Multi-modal Memory (PMM) module captures associations between heterogeneous modalities of image-text pairs belonging to the same person through the Hybrid Cross-modal Matching (HCM) module in a many-to-many mapping fashion. Moreover, the Outlier Pseudo Label Mining (OPLM) module further distinguishes valuable outlier samples from each modality, enhancing the creation of more reliable clusters by mining implicit relationships between image-text pairs. Experimental results demonstrate that our proposed CPCL attains state-of-the-art performance on all three public datasets, with a significant improvement of 11.58%, 8.77% and 5.25% in Rank@1 accuracy on CUHK-PEDES, ICFG-PEDES and RSTPReid datasets, respectively. The code is available at https://github.com/codeGallery24/CPCL.

Regret Optimality of GP-UCB

Gaussian Process Upper Confidence Bound (GP-UCB) is one of the most popular methods for optimizing black-box functions with noisy observations, due to its simple structure and superior performance. Its empirical successes lead to a natural, yet unresolved question: Is GP-UCB regret optimal? In this paper, we offer the first generally affirmative answer to this important open question in the Bayesian optimization literature. We establish new upper bounds on both the simple and cumulative regret of GP-UCB when the objective function to optimize admits certain smoothness property. These upper bounds match the known minimax lower bounds (up to logarithmic factors independent of the feasible region's dimensionality) for optimizing functions with the same smoothness. Intriguingly, our findings indicate that, with the same level of exploration, GP-UCB can simultaneously achieve optimality in both simple and cumulative regret. The crux of our analysis hinges on a refined uniform error bound for online estimation of functions in reproducing kernel Hilbert spaces. This error bound, which we derive from empirical process theory, is of independent interest, and its potential applications may reach beyond the scope of this study.

Learning to Simulate: Generative Metamodeling via Quantile Regression

Stochastic simulation models, while effective in capturing the dynamics of complex systems, are often too slow to run for real-time decision-making. Metamodeling techniques are widely used to learn the relationship between a summary statistic of the outputs (e.g., the mean or quantile) and the inputs of the simulator, so that it can be used in real time. However, this methodology requires the knowledge of an appropriate summary statistic in advance, making it inflexible for many practical situations. In this paper, we propose a new metamodeling concept, called generative metamodeling, which aims to construct a "fast simulator of the simulator". This technique can generate random outputs substantially faster than the original simulation model, while retaining an approximately equal conditional distribution given the same inputs. Once constructed, a generative metamodel can instantaneously generate a large amount of random outputs as soon as the inputs are specified, thereby facilitating the immediate computation of any summary statistic for real-time decision-making. Furthermore, we propose a new algorithm -- quantile-regression-based generative metamodeling (QRGMM) -- and study its convergence and rate of convergence. Extensive numerical experiments are conducted to investigate the empirical performance of QRGMM, compare it with other state-of-the-art generative algorithms, and demonstrate its usefulness in practical real-time decision-making.

Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search

BERT-style models pre-trained on the general corpus (e.g., Wikipedia) and fine-tuned on specific task corpus, have recently emerged as breakthrough techniques in many NLP tasks: question answering, text classification, sequence labeling and so on. However, this technique may not always work, especially for two scenarios: a corpus that contains very different text from the general corpus Wikipedia, or a task that learns embedding spacial distribution for a specific purpose (e.g., approximate nearest neighbor search). In this paper, to tackle the above two scenarios that we have encountered in an industrial e-commerce search system, we propose customized and novel pre-training tasks for two critical modules: user intent detection and semantic embedding retrieval. The customized pre-trained models after fine-tuning, being less than 10% of BERT-base's size in order to be feasible for cost-efficient CPU serving, significantly improve the other baseline models: 1) no pre-training model and 2) fine-tuned model from the official pre-trained BERT using general corpus, on both offline datasets and online system. We have open sourced our datasets for the sake of reproducibility and future works.

Smooth Nested Simulation: Bridging Cubic and Square Root Convergence Rates in High Dimensions

Nested simulation concerns estimating functionals of a conditional expectation via simulation. In this paper, we propose a new method based on kernel ridge regression to exploit the smoothness of the conditional expectation as a function of the multidimensional conditioning variable. Asymptotic analysis shows that the proposed method can effectively alleviate the curse of dimensionality on the convergence rate as the simulation budget increases, provided that the conditional expectation is sufficiently smooth. The smoothness bridges the gap between the cubic root convergence rate (that is, the optimal rate for the standard nested simulation) and the square root convergence rate (that is, the canonical rate for the standard Monte Carlo simulation). We demonstrate the performance of the proposed method via numerical examples from portfolio risk management and input uncertainty quantification.

Self-fulfilling Bandits: Endogeneity Spillover and Dynamic Selection in Algorithmic Decision-making

In this paper, we study endogeneity problems in algorithmic decision-making where data and actions are interdependent. When there are endogenous covariates in a contextual multi-armed bandit model, a novel bias (self-fulfilling bias) arises because the endogeneity of the covariates spills over to the actions. We propose a class of algorithms to correct for the bias by incorporating instrumental variables into leading online learning algorithms. These algorithms also attain regret levels that match the best known lower bound for the cases without endogeneity. To establish the theoretical properties, we develop a general technique that untangles the interdependence between data and actions.

High-Dimensional Simulation Optimization via Brownian Fields and Sparse Grids

High-dimensional simulation optimization is notoriously challenging. We propose a new sampling algorithm that converges to a global optimal solution and suffers minimally from the curse of dimensionality. The algorithm consists of two stages. First, we take samples following a sparse grid experimental design and approximate the response surface via kernel ridge regression with a Brownian field kernel. Second, we follow the expected improvement strategy -- with critical modifications that boost the algorithm's sample efficiency -- to iteratively sample from the next level of the sparse grid. Under mild conditions on the smoothness of the response surface and the simulation noise, we establish upper bounds on the convergence rate for both noise-free and noisy simulation samples. These upper bounds deteriorate only slightly in the dimension of the feasible set, and they can be improved if the objective function is known to be of a higher-order smoothness. Extensive numerical experiments demonstrate that the proposed algorithm dramatically outperforms typical alternatives in practice.

Causal Reinforcement Learning: An Instrumental Variable Approach

In the standard data analysis framework, data is first collected (once for all), and then data analysis is carried out. With the advancement of digital technology, decisionmakers constantly analyze past data and generate new data through the decisions they make. In this paper, we model this as a Markov decision process and show that the dynamic interaction between data generation and data analysis leads to a new type of bias -- reinforcement bias -- that exacerbates the endogeneity problem in standard data analysis. We propose a class of instrument variable (IV)-based reinforcement learning (RL) algorithms to correct for the bias and establish their asymptotic properties by incorporating them into a two-timescale stochastic approximation framework. A key contribution of the paper is the development of new techniques that allow for the analysis of the algorithms in general settings where noises feature time-dependency. We use the techniques to derive sharper results on finite-time trajectory stability bounds: with a polynomial rate, the entire future trajectory of the iterates from the algorithm fall within a ball that is centered at the true parameter and is shrinking at a (different) polynomial rate. We also use the technique to provide formulas for inferences that are rarely done for RL algorithms. These formulas highlight how the strength of the IV and the degree of the noise's time dependency affect the inference.