César Rodríguez

Jiwoo Hong, Noah Lee, Rodrigo Martínez-Castaño et al.

Reinforcement learning with human feedback (RLHF) is shown to largely benefit from precise reward models (RMs). However, recent studies in reward modeling schemes are skewed towards English, limiting the applicability of RLHF in multilingual alignments. In this work, we investigate the cross-lingual transfer of RMs trained in diverse languages, primarily from English. Our experimental results demonstrate the strong cross-lingual transfer of English RMs, exceeding target language RMs by 3~4% average increase in Multilingual RewardBench. Furthermore, we analyze the cross-lingual transfer of RMs through the representation shifts. Finally, we perform multilingual alignment to exemplify how cross-lingual transfer in RM propagates to enhanced multilingual instruction-following capability, along with extensive analyses on off-the-shelf RMs. We release the code, model, and data.

Daniel Schemmel, Julian Büning, César Rodríguez et al.

We describe a technique for systematic testing of multi-threaded programs. We combine Quasi-Optimal Partial-Order Reduction, a state-of-the-art technique that tackles path explosion due to interleaving non-determinism, with symbolic execution to handle data non-determinism. Our technique iteratively and exhaustively finds all executions of the program. It represents program executions using partial orders and finds the next execution using an underlying unfolding semantics. We avoid the exploration of redundant program traces using cutoff events. We implemented our technique as an extension of KLEE and evaluated it on a set of large multi-threaded C programs. Our experiments found several previously undiscovered bugs and undefined behaviors in memcached and GNU sort, showing that the new method is capable of finding bugs in industrial-size benchmarks.

Fabrice Kordon, Alban Linard, Marco Beccuti et al.

This document presents the results of the Model Checking Contest held at Petri Nets 2013 in Milano. This contest aimed at a fair and experimental evaluation of the performances of model checking techniques applied to Petri nets. This is the third edition after two successful editions in 2011 and 2012. The participating tools were compared on several examinations (state space generation and evaluation of several types of formulæ -- reachability, LTL, CTL for various classes of atomic propositions) run on a set of common models (Place/Transition and Symmetric Petri nets). After a short overview of the contest, this paper provides the raw results from the contest, model per model and examination per examination. An HTML version of this report is also provided (http://mcc.lip6.fr).