Collab: Controlled Decoding using Mixture of Agents for LLM Alignment

Alignment of Large Language models (LLMs) is crucial for safe and trustworthy deployment in applications. Reinforcement learning from human feedback (RLHF) has emerged as an effective technique to align LLMs to human preferences and broader utilities, but it requires updating billions of model parameters, which is computationally expensive. Controlled Decoding, by contrast, provides a mechanism for aligning a model at inference time without retraining. However, single-agent decoding approaches often struggle to adapt to diverse tasks due to the complexity and variability inherent in these tasks. To strengthen the test-time performance w.r.t the target task, we propose a mixture of agent-based decoding strategies leveraging the existing off-the-shelf aligned LLM policies. Treating each prior policy as an agent in the spirit of mixture of agent collaboration, we develop a decoding method that allows for inference-time alignment through a token-level selection strategy among multiple agents. For each token, the most suitable LLM is dynamically chosen from a pool of models based on a long-term utility metric. This policy-switching mechanism ensures optimal model selection at each step, enabling efficient collaboration and alignment among LLMs during decoding. Theoretical analysis of our proposed algorithm establishes optimal performance with respect to the target task represented via a target reward for the given off-the-shelf models. We conduct comprehensive empirical evaluations with open-source aligned models on diverse tasks and preferences, which demonstrates the merits of this approach over single-agent decoding baselines. Notably, Collab surpasses the current SoTA decoding strategy, achieving an improvement of up to 1.56x in average reward and 71.89% in GPT-4 based win-tie rate.

Efficient Inverse Multiagent Learning

In this paper, we study inverse game theory (resp. inverse multiagent learning) in which the goal is to find parameters of a game's payoff functions for which the expected (resp. sampled) behavior is an equilibrium. We formulate these problems as generative-adversarial (i.e., min-max) optimization problems, for which we develop polynomial-time algorithms to solve, the former of which relies on an exact first-order oracle, and the latter, a stochastic one. We extend our approach to solve inverse multiagent simulacral learning in polynomial time and number of samples. In these problems, we seek a simulacrum, meaning parameters and an associated equilibrium that replicate the given observations in expectation. We find that our approach outperforms the widely-used ARIMA method in predicting prices in Spanish electricity markets based on time-series data.

ADAGE: A generic two-layer framework for adaptive agent based modelling

Agent-based models (ABMs) are valuable for modelling complex, potentially out-of-equilibria scenarios. However, ABMs have long suffered from the Lucas critique, stating that agent behaviour should adapt to environmental changes. Furthermore, the environment itself often adapts to these behavioural changes, creating a complex bi-level adaptation problem. Recent progress integrating multi-agent reinforcement learning into ABMs introduces adaptive agent behaviour, beginning to address the first part of this critique, however, the approaches are still relatively ad hoc, lacking a general formulation, and furthermore, do not tackle the second aspect of simultaneously adapting environmental level characteristics in addition to the agent behaviours. In this work, we develop a generic two-layer framework for ADaptive AGEnt based modelling (ADAGE) for addressing these problems. This framework formalises the bi-level problem as a Stackelberg game with conditional behavioural policies, providing a consolidated framework for adaptive agent-based modelling based on solving a coupled set of non-linear equations. We demonstrate how this generic approach encapsulates several common (previously viewed as distinct) ABM tasks, such as policy design, calibration, scenario generation, and robust behavioural learning under one unified framework. We provide example simulations on multiple complex economic and financial environments, showing the strength of the novel framework under these canonical settings, addressing long-standing critiques of traditional ABMs.

Regularized Proportional Fairness Mechanism for Resource Allocation Without Money

Mechanism design in resource allocation studies dividing limited resources among self-interested agents whose satisfaction with the allocation depends on privately held utilities. We consider the problem in a payment-free setting, with the aim of maximizing social welfare while enforcing incentive compatibility (IC), i.e., agents cannot inflate allocations by misreporting their utilities. The well-known proportional fairness (PF) mechanism achieves the maximum possible social welfare but incurs an undesirably high exploitability (the maximum unilateral inflation in utility from misreport and a measure of deviation from IC). In fact, it is known that no mechanism can achieve the maximum social welfare and exact incentive compatibility (IC) simultaneously without the use of monetary incentives (Cole et al., 2013). Motivated by this fact, we propose learning an approximate mechanism that desirably trades off the competing objectives. Our main contribution is to design an innovative neural network architecture tailored to the resource allocation problem, which we name Regularized Proportional Fairness Network (RPF-Net). RPF-Net regularizes the output of the PF mechanism by a learned function approximator of the most exploitable allocation, with the aim of reducing the incentive for any agent to misreport. We derive generalization bounds that guarantee the mechanism performance when trained under finite and out-of-distribution samples and experimentally demonstrate the merits of the proposed mechanism compared to the state-of-the-art.

Monty Hall and Optimized Conformal Prediction to Improve Decision-Making with LLMs

Large language models (LLMs) are empowering decision-making in several applications, including tool or API usage and answering multiple-choice questions (MCQs). However, they often make overconfident, incorrect predictions, which can be risky in high-stakes settings like healthcare and finance. To mitigate these risks, recent works have used conformal prediction (CP), a model-agnostic framework for distribution-free uncertainty quantification. CP transforms a \emph{score function} into prediction sets that contain the true answer with high probability. While CP provides this coverage guarantee for arbitrary scores, the score quality significantly impacts prediction set sizes. Prior works have relied on LLM logits or other heuristic scores, lacking quality guarantees. We address this limitation by introducing CP-OPT, an optimization framework to learn scores that minimize set sizes while maintaining coverage. Furthermore, inspired by the Monty Hall problem, we extend CP's utility beyond uncertainty quantification to improve accuracy. We propose \emph{conformal revision of questions} (CROQ) to revise the problem by narrowing down the available choices to those in the prediction set. The coverage guarantee of CP ensures that the correct choice is in the revised question prompt with high probability, while the smaller number of choices increases the LLM's chances of answering it correctly. Experiments on MMLU, ToolAlpaca, and TruthfulQA datasets with Gemma-2, Llama-3 and Phi-3 models show that CP-OPT significantly reduces set sizes while maintaining coverage, and CROQ improves accuracy over the standard inference, especially when paired with CP-OPT scores. Together, CP-OPT and CROQ offer a robust framework for improving both the safety and accuracy of LLM-driven decision-making.

In-Context Learning with Topological Information for Knowledge Graph Completion

Knowledge graphs (KGs) are crucial for representing and reasoning over structured information, supporting a wide range of applications such as information retrieval, question answering, and decision-making. However, their effectiveness is often hindered by incompleteness, limiting their potential for real-world impact. While knowledge graph completion (KGC) has been extensively studied in the literature, recent advances in generative AI models, particularly large language models (LLMs), have introduced new opportunities for innovation. In-context learning has recently emerged as a promising approach for leveraging pretrained knowledge of LLMs across a range of natural language processing tasks and has been widely adopted in both academia and industry. However, how to utilize in-context learning for effective KGC remains relatively underexplored. We develop a novel method that incorporates topological information through in-context learning to enhance KGC performance. By integrating ontological knowledge and graph structure into the context of LLMs, our approach achieves strong performance in the transductive setting i.e., nodes in the test graph dataset are present in the training graph dataset. Furthermore, we apply our approach to KGC in the more challenging inductive setting, i.e., nodes in the training graph dataset and test graph dataset are disjoint, leveraging the ontology to infer useful information about missing nodes which serve as contextual cues for the LLM during inference. Our method demonstrates superior performance compared to baselines on the ILPC-small and ILPC-large datasets.

Approximate Equivariance in Reinforcement Learning

Equivariant neural networks have shown great success in reinforcement learning, improving sample efficiency and generalization when there is symmetry in the task. However, in many problems, only approximate symmetry is present, which makes imposing exact symmetry inappropriate. Recently, approximately equivariant networks have been proposed for supervised classification and modeling physical systems. In this work, we develop approximately equivariant algorithms in reinforcement learning (RL). We define approximately equivariant MDPs and theoretically characterize the effect of approximate equivariance on the optimal Q function. We propose novel RL architectures using relaxed group convolutions and experiment on several continuous control domains and stock trading with real financial data. Our results demonstrate that approximate equivariance matches prior work when exact symmetries are present, and outperforms them when domains exhibit approximate symmetry. As an added byproduct of these techniques, we observe increased robustness to noise at test time.

Simulate and Optimise: A two-layer mortgage simulator for designing novel mortgage assistance products

We develop a novel two-layer approach for optimising mortgage relief products through a simulated multi-agent mortgage environment. While the approach is generic, here the environment is calibrated to the US mortgage market based on publicly available census data and regulatory guidelines. Through the simulation layer, we assess the resilience of households to exogenous income shocks, while the optimisation layer explores strategies to improve the robustness of households to these shocks by making novel mortgage assistance products available to households. Households in the simulation are adaptive, learning to make mortgage-related decisions (such as product enrolment or strategic foreclosures) that maximize their utility, balancing their available liquidity and equity. We show how this novel two-layer simulation approach can successfully design novel mortgage assistance products to improve household resilience to exogenous shocks, and balance the costs of providing such products through post-hoc analysis. Previously, such analysis could only be conducted through expensive pilot studies involving real participants, demonstrating the benefit of the approach for designing and evaluating financial products.

Scalable Representation Learning for Multimodal Tabular Transactions

Large language models (LLMs) are primarily designed to understand unstructured text. When directly applied to structured formats such as tabular data, they may struggle to discern inherent relationships and overlook critical patterns. While tabular representation learning methods can address some of these limitations, existing efforts still face challenges with sparse high-cardinality fields, precise numerical reasoning, and column-heavy tables. Furthermore, leveraging these learned representations for downstream tasks through a language based interface is not apparent. In this paper, we present an innovative and scalable solution to these challenges. Concretely, our approach introduces a multi-tier partitioning mechanism that utilizes power-law dynamics to handle large vocabularies, an adaptive quantization mechanism to impose priors on numerical continuity, and a distinct treatment of core-columns and meta-information columns. To facilitate instruction tuning on LLMs, we propose a parameter efficient decoder that interleaves transaction and text modalities using a series of adapter layers, thereby exploiting rich cross-task knowledge. We validate the efficacy of our solution on a large-scale dataset of synthetic payments transactions.

GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment

Large Language Models (LLMs) exhibit impressive capabilities but require careful alignment with human preferences. Traditional training-time methods finetune LLMs using human preference datasets but incur significant training costs and require repeated training to handle diverse user preferences. Test-time alignment methods address this by using reward models (RMs) to guide frozen LLMs without retraining. However, existing test-time approaches rely on trajectory-level RMs which are designed to evaluate complete responses, making them unsuitable for autoregressive text generation that requires computing next-token rewards from partial responses. To address this, we introduce GenARM, a test-time alignment approach that leverages the Autoregressive Reward Model--a novel reward parametrization designed to predict next-token rewards for efficient and effective autoregressive generation. Theoretically, we demonstrate that this parametrization can provably guide frozen LLMs toward any distribution achievable by traditional RMs within the KL-regularized reinforcement learning framework. Experimental results show that GenARM significantly outperforms prior test-time alignment baselines and matches the performance of training-time methods. Additionally, GenARM enables efficient weak-to-strong guidance, aligning larger LLMs with smaller RMs without the high costs of training larger models. Furthermore, GenARM supports multi-objective alignment, allowing real-time trade-offs between preference dimensions and catering to diverse user preferences without retraining.