Advancing LLM Reasoning Generalists with Preference Trees

We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Finetuned from Mistral-7B and CodeLlama-70B, Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks covering mathematics, code generation, and logical reasoning problems. Notably, Eurus-70B beats GPT-3.5 Turbo in reasoning through a comprehensive benchmarking across 12 tests covering five tasks, and achieves a 33.3% pass@1 accuracy on LeetCode and 32.6% on TheoremQA, two challenging benchmarks, substantially outperforming existing open-source models by margins more than 13.3%. The strong performance of Eurus can be primarily attributed to UltraInteract, our newly-curated large-scale, high-quality alignment dataset specifically designed for complex reasoning tasks. UltraInteract can be used in both supervised fine-tuning and preference learning. For each instruction, it includes a preference tree consisting of (1) reasoning chains with diverse planning strategies in a unified format, (2) multi-turn interaction trajectories with the environment and the critique, and (3) pairwise data to facilitate preference learning. UltraInteract allows us to conduct an in-depth exploration of preference learning for reasoning tasks. Our investigation reveals that some well-established preference learning algorithms may be less suitable for reasoning tasks compared to their effectiveness in general conversations. Inspired by this, we derive a novel reward modeling objective which, together with UltraInteract, leads to a strong reward model.

Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment

Alignment in artificial intelligence pursues the consistency between model responses and human preferences as well as values. In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment tax" -a compromise where enhancements in alignment within one objective (e.g.,harmlessness) can diminish performance in others (e.g.,helpfulness). However, existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. To navigate this challenge, we argue the prominence of grounding LLMs with evident preferences. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives, thereby guiding the model to generate responses that meet the requirements. Our experimental analysis reveals that the aligned models can provide responses that match various preferences among the "3H" (helpfulness, honesty, harmlessness) desiderata. Furthermore, by introducing diverse data and alignment goals, we surpass baseline methods in aligning with single objectives, hence mitigating the impact of the alignment tax and achieving Pareto improvements in multi-objective alignment.

Exploration into Optimal State Estimation with Event-triggered Communication

This paper deals with the problem of remote estimation of the state of a discrete-time stochastic linear system observed by a sensor with computational capacity to calculate local estimates. We design an event-triggered communication (ETC) scheme and a remote state estimator to optimally calibrate the tradeoff between system performance and limited communication resources. The novel communication scheme is the time-varying thresholding version for the cumulative innovation-driven communication scheme in [1], and its transmission probability is given. We derive the corresponding remote minimum mean square error (MMSE) estimator and present a tight upper bound for its MSE matrices. We also show that by employing a couple of weak assumptions, the optimality problem becomes (asymptotically) exact and can be addressed in an Markov Decision Process (MDP) framework, which delivers optimal policy and cost in an algorithmic procedure. The simulation results illustrate the effectiveness of our approach.

Country Image in COVID-19 Pandemic: A Case Study of China

Country image has a profound influence on international relations and economic development. In the worldwide outbreak of COVID-19, countries and their people display different reactions, resulting in diverse perceived images among foreign public. Therefore, in this study, we take China as a specific and typical case and investigate its image with aspect-based sentiment analysis on a large-scale Twitter dataset. To our knowledge, this is the first study to explore country image in such a fine-grained way. To perform the analysis, we first build a manually-labeled Twitter dataset with aspect-level sentiment annotations. Afterward, we conduct the aspect-based sentiment analysis with BERT to explore the image of China. We discover an overall sentiment change from non-negative to negative in the general public, and explain it with the increasing mentions of negative ideology-related aspects and decreasing mentions of non-negative fact-based aspects. Further investigations into different groups of Twitter users, including U.S. Congress members, English media, and social bots, reveal different patterns in their attitudes toward China. This study provides a deeper understanding of the changing image of China in COVID-19 pandemic. Our research also demonstrates how aspect-based sentiment analysis can be applied in social science researches to deliver valuable insights.

Improving Stock Movement Prediction with Adversarial Training

This paper contributes a new machine learning solution for stock movement prediction, which aims to predict whether the price of a stock will be up or down in the near future. The key novelty is that we propose to employ adversarial training to improve the generalization of a recurrent neural network model. The rationality of adversarial training here is that the input features to stock prediction are typically based on stock price, which is essentially a stochastic variable and continuously changed with time by nature. As such, normal training with stationary price-based features (e.g. the closing price) can easily overfit the data, being insufficient to obtain reliable models. To address this problem, we propose to add perturbations to simulate the stochasticity of continuous price variable, and train the model to work well under small yet intentional perturbations. Extensive experiments on two real-world stock data show that our method outperforms the state-of-the-art solution with 3.11% relative improvements on average w.r.t. accuracy, verifying the usefulness of adversarial training for stock prediction task. Codes will be made available upon acceptance.