Víctor Gallego

Victor Gallego

In this work, we address the problem of directing the text generation of a language model (LM) towards a desired behavior, aligning the generated text with the preferences of the human operator. We propose using another, instruction-tuned language model as a critic reward model in a zero-shot way thanks to the prompt of a Yes-No question that represents the user preferences, without requiring further labeled data. This zero-shot reward model provides the learning signal to further fine-tune the base LM using Reinforcement Learning from AI Feedback (RLAIF); yet our approach is also compatible in other contexts such as quality-diversity search. Extensive evidence of the capabilities of the proposed ZYN framework is provided through experiments in different domains related to text generation, including detoxification; optimizing sentiment of movie reviews, or any other attribute; steering the opinion about a particular topic the model may have; and personalizing prompt generators for text-to-image tasks. Code available at \url{https://github.com/vicgalle/zero-shot-reward-models/}.

Víctor Gallego

We present Metal-Sci, a 10-task benchmark of scientific Apple Silicon Metal compute kernels spanning six optimization regimes (stencils, all-pairs in $n$-body problems, multi-field Boltzmann, neighbor-list molecular dynamics, multi-kernel PDE, FFT). Each task ships a CPU reference, a roofline-anchored fitness function, and a held-out generalization size. We pair the benchmark with a lightweight harness for automatic kernel search that runtime-compiles each candidate, scores it against the roofline across multiple sizes, and feeds structured compile and per-size correctness diagnostics back to a frozen LLM driving a $(1{+}1)$ evolutionary loop. We report matched single-model sweeps of Claude Opus 4.7, Gemini 3.1 Pro, and GPT 5.5 on M1 Pro: in-distribution self-speedups span $1.00\times$ to $10.7\times$. Beyond raw speedup, our central methodological claim is structural: the held-out gate scoring function $Φ_\mathcal{T}$ (evaluated once at end-of-run on a configuration the agent never sees during search) functions as a cheap mechanical oversight primitive on this automatic search loop, catching e.g. an Opus template <uint D> HMC win that returns wrong samples at unseen dimensions, and a GPT FFT3D best that wins in-distribution at $2.95\times$ speedup but collapses to $0.23\times$ on a $256^3$ held-out cube, a silent regression that the in-distribution score alone cannot see. Code at https://github.com/vicgalle/metal-sci-kernels

Victor Gallego

State-of-the-art language model fine-tuning techniques, such as Direct Preference Optimization (DPO), restrict user control by hard-coding predefined behaviors into the model. To address this, we propose a novel method, Configurable Safety Tuning (CST), that augments DPO using synthetic preference data to facilitate flexible safety configuration of LLMs at inference time. CST overcomes the constraints of vanilla DPO by introducing a system prompt specifying safety configurations, enabling LLM deployers to disable/enable safety preferences based on their need, just changing the system prompt. Our experimental evaluations indicate that CST successfully manages different safety configurations and retains the original functionality of LLMs, showing it is a robust method for configurable deployment. Data and models available at https://github.com/vicgalle/configurable-safety-tuning

Víctor Gallego

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating synthetic data using self-critique prompting by a teacher LLM and then utilising a generalized DPO loss function to distil to a student LLM. The loss function incorporates an additional external reward model to improve the quality of synthetic data, making rDPO robust to potential noise in the synthetic dataset. rDPO is shown to be effective in a diverse set of behavioural alignment tasks, such as improved safety, robustness against role-playing, and reduced sycophancy. Code to be released at https://github.com/vicgalle/refined-dpo.

Victor Gallego

Recently, large multimodal models, such as CLIP and Stable Diffusion have experimented tremendous successes in both foundations and applications. However, as these models increase in parameter size and computational requirements, it becomes more challenging for users to personalize them for specific tasks or preferences. In this work, we address the problem of adapting the previous models towards sets of particular human preferences, aligning the retrieved or generated images with the preferences of the user. We leverage the Bradley-Terry preference model to develop a fast adaptation method that efficiently fine-tunes the original model, with few examples and with minimal computing resources. Extensive evidence of the capabilities of this framework is provided through experiments in different domains related to multimodal text and image understanding, including preference prediction as a reward model, and generation tasks.

Víctor Gallego

We propose a framework that amortizes the cost of inference-time reasoning by converting transient critiques into retrievable guidelines, through a file-based memory system and agent-controlled tool calls. We evaluate this method on the Rubric Feedback Bench, a novel dataset for rubric-based learning. Experiments demonstrate that our augmented LLMs rapidly match the performance of test-time refinement pipelines while drastically reducing inference cost.

Víctor Gallego

Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic preferences by introducing Configurable Preference Tuning (CPT), a novel framework for endowing language models with the ability to dynamically adjust their behavior based on explicit, human-interpretable directives. CPT leverages synthetically generated preference data, conditioned on system prompts derived from structured, fine-grained rubrics that define desired attributes like writing style. By fine-tuning with these rubric-guided preferences, the LLM learns to modulate its outputs at inference time in response to the system prompt, without retraining. This approach not only offers fine-grained control but also provides a mechanism for modeling more nuanced and context-dependent human feedback. Several experimental artifacts, such as training code, generated datasets and fine-tuned models are released at https://github.com/vicgalle/configurable-preference-tuning

Victor Gallego

The robustness of large language models (LLMs) against adversarial manipulations, such as jailbreak attacks, remains a significant challenge. In this work, we propose an approach that enhances the self-critique capability of the LLM and further fine-tunes it over sanitized synthetic data. This is done with the addition of an external critic model that can be merged with the original, thus bolstering self-critique capabilities and improving the robustness of the LLMs response to adversarial prompts. Our results demonstrate that the combination of merging and self-critique can reduce the attack success rate of adversaries significantly, thus offering a promising defense mechanism against jailbreak attacks. Code, data and models released at https://github.com/vicgalle/merging-self-critique-jailbreaks .

Víctor Gallego

The rampant adoption of ML methodologies has revealed that models are usually adopted to make decisions without taking into account the uncertainties in their predictions. More critically, they can be vulnerable to adversarial examples. Thus, we believe that developing ML systems that take into account predictive uncertainties and are robust against adversarial examples is a must for critical, real-world tasks. We start with a case study in retailing. We propose a robust implementation of the Nerlove-Arrow model using a Bayesian structural time series model. Its Bayesian nature facilitates incorporating prior information reflecting the manager's views, which can be updated with relevant data. However, this case adopted classical Bayesian techniques, such as the Gibbs sampler. Nowadays, the ML landscape is pervaded with neural networks and this chapter also surveys current developments in this sub-field. Then, we tackle the problem of scaling Bayesian inference to complex models and large data regimes. In the first part, we propose a unifying view of two different Bayesian inference algorithms, Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) and Stein Variational Gradient Descent (SVGD), leading to improved and efficient novel sampling schemes. In the second part, we develop a framework to boost the efficiency of Bayesian inference in probabilistic models by embedding a Markov chain sampler within a variational posterior approximation. After that, we present an alternative perspective on adversarial classification based on adversarial risk analysis, and leveraging the scalable Bayesian approaches from chapter 2. In chapter 4 we turn to reinforcement learning, introducing Threatened Markov Decision Processes, showing the benefits of accounting for adversaries in RL while the agent learns.

Víctor Gallego, Roi Naveiro, David Ríos Insua et al.

Data sharing issues pervade online social and economic environments. To foster social progress, it is important to develop models of the interaction between data producers and consumers that can promote the rise of cooperation between the involved parties. We formalize this interaction as a game, the data sharing game, based on the Iterated Prisoner's Dilemma and deal with it through multi-agent reinforcement learning techniques. We consider several strategies for how the citizens may behave, depending on the degree of centralization sought. Simulations suggest mechanisms for cooperation to take place and, thus, achieve maximum social utility: data consumers should perform some kind of opponent modeling, or a regulator should transfer utility between both players and incentivise them.

David Rios Insua, Roi Naveiro, Victor Gallego et al.

Adversarial Machine Learning (AML) is emerging as a major field aimed at protecting machine learning (ML) systems against security threats: in certain scenarios there may be adversaries that actively manipulate input data to fool learning systems. This creates a new class of security vulnerabilities that ML systems may face, and a new desirable property called adversarial robustness essential to trust operations based on ML outputs. Most work in AML is built upon a game-theoretic modelling of the conflict between a learning system and an adversary, ready to manipulate input data. This assumes that each agent knows their opponent's interests and uncertainty judgments, facilitating inferences based on Nash equilibria. However, such common knowledge assumption is not realistic in the security scenarios typical of AML. After reviewing such game-theoretic approaches, we discuss the benefits that Bayesian perspectives provide when defending ML-based systems. We demonstrate how the Bayesian approach allows us to explicitly model our uncertainty about the opponent's beliefs and interests, relaxing unrealistic assumptions, and providing more robust inferences. We illustrate this approach in supervised learning settings, and identify relevant future research problems.

Victor Gallego, David Rios Insua

A framework to boost the efficiency of Bayesian inference in probabilistic programs is introduced by embedding a sampler inside a variational posterior approximation. We call it the refined variational approximation. Its strength lies both in ease of implementation and automatically tuning of the sampler parameters to speed up mixing time using automatic differentiation. Several strategies to approximate \emph{evidence lower bound} (ELBO) computation are introduced. Experimental evidence of its efficient performance is shown solving an influence diagram in a high-dimensional space using a conditional variational autoencoder (cVAE) as a deep Bayes classifier; an unconditional VAE on density estimation tasks; and state-space models for time-series data.

Victor Gallego, Roi Naveiro, David Rios Insua et al.

We introduce Threatened Markov Decision Processes (TMDPs) as an extension of the classical Markov Decision Process framework for Reinforcement Learning (RL). TMDPs allow suporting a decision maker against potential opponents in a RL context. We also propose a level-k thinking scheme resulting in a novel learning approach to deal with TMDPs. After introducing our framework and deriving theoretical results, relevant empirical evidence is given via extensive experiments, showing the benefits of accounting for adversaries in RL while the agent learns

Victor Gallego, David Rios Insua

We propose a unifying view of two different Bayesian inference algorithms, Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) and Stein Variational Gradient Descent (SVGD), leading to improved and efficient novel sampling schemes. We show that SVGD combined with a noise term can be framed as a multiple chain SG-MCMC method. Instead of treating each parallel chain independently from others, our proposed algorithm implements a repulsive force between particles, avoiding collapse and facilitating a better exploration of the parameter space. We also show how the addition of this noise term is necessary to obtain a valid SG-MCMC sampler, a significant difference with SVGD. Experiments with both synthetic distributions and real datasets illustrate the benefits of the proposed scheme.

Victor Gallego, Roi Naveiro, David Rios Insua

In several reinforcement learning (RL) scenarios, mainly in security settings, there may be adversaries trying to interfere with the reward generating process. In this paper, we introduce Threatened Markov Decision Processes (TMDPs), which provide a framework to support a decision maker against a potential adversary in RL. Furthermore, we propose a level-$k$ thinking scheme resulting in a new learning framework to deal with TMDPs. After introducing our framework and deriving theoretical results, relevant empirical evidence is given via extensive experiments, showing the benefits of accounting for adversaries while the agent learns.

Víctor Gallego, Pablo Suárez-García, Pablo Angulo et al.

We propose a robust implementation of the Nerlove--Arrow model using a Bayesian structural time series model to explain the relationship between advertising expenditures of a country-wide fast-food franchise network with its weekly sales. Thanks to the flexibility and modularity of the model, it is well suited to generalization to other markets or situations. Its Bayesian nature facilitates incorporating \emph{a priori} information (the manager's views), which can be updated with relevant data. This aspect of the model will be used to present a strategy of budget scheduling across time and channels.