Jiaying Lin, Seongho Son, Nam Phuong Tran, Long Tran-thanh, Ilija Bogunovic, Debmalya Mandal
原文摘要
Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of sufficient data in low-resource language alignment, we propose a meta-learning framework for Reinforcement Learning from Human Feedback and Direct Preference Optimization. By leveraging preference data from other languages, our framework learns a transferable initialization that enables effective adaptation to a target language with minimal data. We provide theoretical guarantees for both the meta-reward modeling and meta-policy optimization settings, and empirically demonstrate the effectiveness of our approach on multilingual benchmarks. In an extremely low-resource setting with only 100 target-language preference samples, our approach achieves up to $33.4\%$ win-rate improvements over baseline methods, and consistently outperforms baselines across multiple target languages and model scales. Our approaches retain these advantages across different combinations of meta-training languages and varying linguistic distances from the target languages.
Constrained Markov decision processes (CMDPs) typically bound expected cumulative cost from an initial state. Such a guarantee can be insufficient when a policy must remain feasible after every history it may encounter. We introduce \emph{subprocess-constrained MDPs} (S-CMDPs), which require the expected discounted cost of each continuation, conditional on any reachable history, to satisfy a bound determined by the current state. This stronger requirement changes the structure and complexity of the problem: we show that stationary policies can be strictly suboptimal, and finding even an approximately optimal stationary policy is NP-hard. We adapt a recently introduced value-set iteration framework to show that history-dependent policies surprisingly overcome both obstacles. Our polynomial-time algorithm represents such a policy implicitly: its expected reward is within $ε$ of the optimal feasible value, it violates each subprocess cost bound by at most $δ$, and its action distribution can be computed in polynomial time for any given history.
Conformal prediction (CP) provides a distribution-free approach to uncertainty quantification with finite-sample guarantees. However, applying CP to graph neural networks (GNNs) remains challenging as the combinatorial nature of graphs often leads to insufficiently certain predictions and indiscriminative embeddings. Existing methods primarily rely on embedding-space proximity for localization, which can be unreliable for graphs and yield uneven coverage across different graph regions. We propose GRAPHLCP, a proximity-based localized CP framework that incorporates graph topology and inter-node dependencies into localization and weighting. Our approach introduces a feature-aware densification step to mitigate locality bias in sparse graphs, followed by a Personalized PageRank-based kernel computation to model structural proximity. This enables topology-dependent anchor sampling and calibration weighting that captures both local and long-range dependencies. Extensive experiments on regression and classification datasets demonstrate that GRAPHLCP improves test-conditional coverage without excessive conservativeness, while preserving finite-sample marginal coverage.