Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs by training a reward model (RM) on human preferences and fine-tuning the LLMs to maximize RM feedback. Despite its effectiveness and popularity, RLHF is prone to biased local optimization. It means RM fails to provide feedback that accurately aligns with human preference, causing LLMs to explore unexpected generalizations, and failing to achieve alignment objectives. To mitigate this issue, we propose a novel \textit{sequence-to-sequence (seq2seq) reward modeling} method. Its key insight is that learning from language feedback rather than scalar feedback improves RLHF without additional annotations. We replaced the reward modeling target from binary maximum likelihood estimation (MLE) with sequence MLE. This method enables richer and fine-grained language feedback without additional annotations, models, or training stages. Our experiments demonstrated its effectiveness, specifically, reducing the refusal-to-response paradigm in single-turn safety dialogues and the long-response bias in text summarization tasks. We provide further analysis that seq2seq RM improves RLHF performance across 2B and 7B LLMs on 3 NLP tasks, achieving an average win rate of 76.9\%. We further show that seq2seq RM can still improve the performance of RLHF under out-of-distribution prompts.

The dominant practice of AI alignment assumes (1) that preferences are an adequate representation of human values, (2) that human rationality can be understood in terms of maximizing the satisfaction of preferences, and (3) that AI systems should be aligned with the preferences of one or more humans to ensure that they behave safely and in accordance with our values. Whether implicitly followed or explicitly endorsed, these commitments constitute what we term a preferentist approach to AI alignment. In this paper, we characterize and challenge the preferentist approach, describing conceptual and technical alternatives that are ripe for further research. We first survey the limits of rational choice theory as a descriptive model, explaining how preferences fail to capture the thick semantic content of human values, and how utility representations neglect the possible incommensurability of those values. We then critique the normativity of expected utility theory (EUT) for humans and AI, drawing upon arguments showing how rational agents need not comply with EUT, while highlighting how EUT is silent on which preferences are normatively acceptable. Finally, we argue that these limitations motivate a reframing of the targets of AI alignment: Instead of alignment with the preferences of a human user, developer, or humanity-writ-large, AI systems should be aligned with normative standards appropriate to their social roles, such as the role of a general-purpose assistant. Furthermore, these standards should be negotiated and agreed upon by all relevant stakeholders. On this alternative conception of alignment, a multiplicity of AI systems will be able to serve diverse ends, aligned with normative standards that promote mutual benefit and limit harm despite our plural and divergent values.

Balancing computational efficiency with robust predictive performance is crucial in supervised learning, especially for critical applications. Standard deep learning models, while accurate and scalable, often lack probabilistic features like calibrated predictions and uncertainty quantification. Bayesian methods address these issues but can be computationally expensive as model and data complexity increase. Previous work shows that fast variational methods can reduce the compute requirements of Bayesian methods by eliminating the need for gradient computation or sampling, but are often limited to simple models. We demonstrate that conditional mixture networks (CMNs), a probabilistic variant of the mixture-of-experts (MoE) model, are suitable for fast, gradient-free inference and can solve complex classification tasks. CMNs employ linear experts and a softmax gating network. By exploiting conditional conjugacy and P\'olya-Gamma augmentation, we furnish Gaussian likelihoods for the weights of both the linear experts and the gating network. This enables efficient variational updates using coordinate ascent variational inference (CAVI), avoiding traditional gradient-based optimization. We validate this approach by training two-layer CMNs on standard benchmarks from the UCI repository. Our method, CAVI-CMN, achieves competitive and often superior predictive accuracy compared to maximum likelihood estimation (MLE) with backpropagation, while maintaining competitive runtime and full posterior distributions over all model parameters. Moreover, as input size or the number of experts increases, computation time scales competitively with MLE and other gradient-based solutions like black-box variational inference (BBVI), making CAVI-CMN a promising tool for deep, fast, and gradient-free Bayesian networks.

Beyond maximum likelihood estimation (MLE), the standard objective of a language model (LM) that optimizes good examples probabilities, many studies have explored ways that also penalize bad examples for enhancing the quality of output distribution, including unlikelihood training, exponential maximizing average treatment effect (ExMATE), and direct preference optimization (DPO). To systematically compare these methods and further provide a unified recipe for LM optimization, in this paper, we present a unique angle of gradient analysis of loss functions that simultaneously reward good examples and penalize bad ones in LMs. Through both mathematical results and experiments on CausalDialogue and Anthropic HH-RLHF datasets, we identify distinct functional characteristics among these methods. We find that ExMATE serves as a superior surrogate for MLE, and that combining DPO with ExMATE instead of MLE further enhances both the statistical (5-7%) and generative (+18% win rate) performance.

Psychological support hotlines are an effective suicide prevention measure that typically relies on professionals using suicide risk assessment scales to predict individual risk scores. However, the accuracy of scale-based predictive methods for suicide risk assessment can vary widely depending on the expertise of the operator. This limitation underscores the need for more reliable methods, prompting this research's innovative exploration of the use of artificial intelligence to improve the accuracy and efficiency of suicide risk prediction within the context of psychological support hotlines. The study included data from 1,549 subjects from 2015-2017 in China who contacted a psychological support hotline. Each participant was followed for 12 months to identify instances of suicidal behavior. We proposed a novel multi-task learning method that uses the large-scale pre-trained model Whisper for feature extraction and fits psychological scales while predicting the risk of suicide. The proposed method yields a 2.4\% points improvement in F1-score compared to the traditional manual approach based on the psychological scales. Our model demonstrated superior performance compared to the other eight popular models. To our knowledge, this study is the first to apply deep learning to long-term speech data to predict suicide risk in China, indicating grate potential for clinical applications. The source code is publicly available at: \url{https://github.com/songchangwei/Suicide-Risk-Prediction}.

Breast cancer is one of the two cancers responsible for the most deaths in women, with about 42,000 deaths each year in the US. That there are over 300,000 breast cancers newly diagnosed each year suggests that only a fraction of the cancers result in mortality. Thus, most of the women undergo seemingly curative treatment for localized cancers, but a significant later succumb to metastatic disease for which current treatments are only temporizing for the vast majority. The current prognostic metrics are of little actionable value for 4 of the 5 women seemingly cured after local treatment, and many women are exposed to morbid and even mortal adjuvant therapies unnecessarily, with these adjuvant therapies reducing metastatic recurrence by only a third. Thus, there is a need for better prognostics to target aggressive treatment at those who are likely to relapse and spare those who were actually cured. While there is a plethora of molecular and tumor-marker assays in use and under-development to detect recurrence early, these are time consuming, expensive and still often un-validated as to actionable prognostic utility. A different approach would use large data techniques to determine clinical and histopathological parameters that would provide accurate prognostics using existing data. Herein, we report on machine learning, together with grid search and Bayesian Networks to develop algorithms that present a AUC of up to 0.9 in ROC analyses, using only extant data. Such algorithms could be rapidly translated to clinical management as they do not require testing beyond routine tumor evaluations.

Variational continual learning (VCL) is a turn-key learning algorithm that has state-of-the-art performance among the best continual learning models. In our work, we explore an extension of the generalized variational continual learning (GVCL) model, named AutoVCL, which combines task heuristics for informed learning and model optimization. We demonstrate that our model outperforms the standard GVCL with fixed hyperparameters, benefiting from the automatic adjustment of the hyperparameter based on the difficulty and similarity of the incoming task compared to the previous tasks.

Learning a transition model via Maximum Likelihood Estimation (MLE) followed by planning inside the learned model is perhaps the most standard and simplest Model-based Reinforcement Learning (RL) framework. In this work, we show that such a simple Model-based RL scheme, when equipped with optimistic and pessimistic planning procedures, achieves strong regret and sample complexity bounds in online and offline RL settings. Particularly, we demonstrate that under the conditions where the trajectory-wise reward is normalized between zero and one and the transition is time-homogenous, it achieves horizon-free and second-order bounds. Horizon-free means that our bounds have no polynomial dependence on the horizon of the Markov Decision Process. A second-order bound is a type of instance-dependent bound that scales with respect to the variances of the returns of the policies which can be small when the system is nearly deterministic and (or) the optimal policy has small values. We highlight that our algorithms are simple, fairly standard, and indeed have been extensively studied in the RL literature: they learn a model via MLE, build a version space around the MLE solution, and perform optimistic or pessimistic planning depending on whether operating in the online or offline mode. These algorithms do not rely on additional specialized algorithmic designs such as learning variances and performing variance-weighted learning and thus can leverage rich function approximations that are significantly beyond linear or tabular structures. The simplicity of the algorithms also implies that our horizon-free and second-order regret analysis is actually standard and mainly follows the general framework of optimism/pessimism in the face of uncertainty.

Neural Networks (NNs) are promising models for refining the accuracy of molecular dynamics, potentially opening up new fields of application. Typically trained bottom-up, atomistic NN potential models can reach first-principle accuracy, while coarse-grained implicit solvent NN potentials surpass classical continuum solvent models. However, overcoming the limitations of costly generation of accurate reference data and data inefficiency of common bottom-up training demands efficient incorporation of data from many sources. This paper introduces the framework chemtrain to learn sophisticated NN potential models through customizable training routines and advanced training algorithms. These routines can combine multiple top-down and bottom-up algorithms, e.g., to incorporate both experimental and simulation data or pre-train potentials with less costly algorithms. chemtrain provides an object-oriented high-level interface to simplify the creation of custom routines. On the lower level, chemtrain relies on JAX to compute gradients and scale the computations to use available resources. We demonstrate the simplicity and importance of combining multiple algorithms in the examples of parametrizing an all-atomistic model of titanium and a coarse-grained implicit solvent model of alanine dipeptide.

Generative Flow Networks (GFlowNets) are a class of generative models that sample objects in proportion to a specified reward function through a learned policy. They can be trained either on-policy or off-policy, needing a balance between exploration and exploitation for fast convergence to a target distribution. While exploration strategies for discrete GFlowNets have been studied, exploration in the continuous case remains to be investigated, despite the potential for novel exploration algorithms due to the local connectedness of continuous domains. Here, we introduce Adapted Metadynamics, a variant of metadynamics that can be applied to arbitrary black-box reward functions on continuous domains. We use Adapted Metadynamics as an exploration strategy for continuous GFlowNets. We show three continuous domains where the resulting algorithm, MetaGFN, accelerates convergence to the target distribution and discovers more distant reward modes than previous off-policy exploration strategies used for GFlowNets.