7 papers
Who Is Really Playing? Strategic Interaction in AI-Guided Populations
Jonathan Shaki, Eden Hartman, Sarit Kraus +1
AI systems in general, and Large language models (LLMs), in particular, are increasingly used to provide instructions to many agents who interact with one another. Such shared reli…
Ensemble Self-Training for Unsupervised Machine Translation
Ido Aharon, Jonathan Shaki, Sarit Kraus
We present an ensemble-driven self-training framework for unsupervised neural machine translation (UNMT). Starting from a primary language pair, we train multiple UNMT models that…
Pro-AI Bias in Large Language Models
Benaya Trabelsi, Jonathan Shaki, Sarit Kraus
Large language models (LLMs) are increasingly employed for decision-support across multiple domains. We investigate whether these models display a systematic preferential bias in f…
Persuading Stable Matching
Jonathan Shaki, Jiarui Gan, Sarit Kraus
In bipartite matching problems, agents on two sides of a graph want to be paired according to their preferences. The stability of a matching depends on these preferences, which in…
Out-of-Context Reasoning in Large Language Models
Jonathan Shaki, Emanuele La Malfa, Michael Wooldridge +1
We study how large language models (LLMs) reason about memorized knowledge through simple binary relations such as equality (), inequality (), and inclusion (). Unli…
Voter Priming Campaigns: Strategies, Equilibria, and Algorithms
Jonathan Shaki, Yonatan Aumann, Sarit Kraus
Issue salience is a major determinant in voters' decisions. Candidates and political parties campaign to shift salience to their advantage - a process termed priming. We study the…