collaborators

11 papers

cs.LG2026

Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization

Mélissa Tamine, Otmane Sakhi, Benjamin Heymann +2

Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multiple sources. The standard game-t…

stat.ML2026

Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation

Imad Aouali, Otmane Sakhi

Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits. Recent advances in OPL primarily optimize OPE estimato…

stat.ML2026

Exploiting Similarities in A/B Testing with Off-Policy Estimation

Otmane Sakhi, Alexandre Gilotte, David Rohde

We study A/B testing, the standard protocol for measuring the performance gain of a new decision system relative to a baseline. Traditional A/B testing treats both systems as black…

cs.LG2026

Off-Policy Learning to Reason Works Because It Is More Pessimistic Than You Think

Otmane Sakhi, Aleksei Arzhantsev, Imad Aouali +1

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates…

cs.LG2026

Self-Consistency via Marginal Sharpening

Aleksei Arzhantsev, Otmane Sakhi, Nicolas Chopin

Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so by sharpening the distribution…

cs.LG2026

Learning to Bid in Repeated Second-Price Auctions with Dynamic Values and Aggregated Feedback

Benjamin Heymann, Otmane Sakhi

We study the problem of learning to bid when the bidder's value is dynamic, i.e., when the current value depends on past outcomes. Specifically, we consider a bidder participating…